Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 2-LLAMASCOPE-RES-32K
    6. 0
    Prev
    Next
    INDEX
    Explanations

    The phrase "let alone" is used to introduce a second clause that is even less likely or less possible than the first clause. The two clauses typically describe a hierarchy of increasing improbability or difficulty.

    eleuther_acts_top20 · gemini-1.5-flashTriggered by @johnny

    phrases related to solitude and isolation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oleon
    -0.16
    ãĢħ
    -0.15
    ë¸
    -0.14
     PÅĻ
    -0.14
    etimes
    -0.14
    ãĥİ
    -0.14
    uler
    -0.13
    ler
    -0.13
    zzo
    -0.13
    CurrentValue
    -0.13
    POSITIVE LOGITS
    utm
    0.17
    ut
    0.16
    edd
    0.15
    bulk
    0.15
    uty
    0.14
    ipo
    0.14
     vid
    0.14
    ernal
    0.13
    jen
    0.13
    oly
    0.13
    Activations Density 0.187%

    No Known Activations