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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-LLAMASCOPE-RES-32K
    6. 16599
    Prev
    Next
    INDEX
    Explanations

    single quotation marks and punctuation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccione
    -0.16
    osu
    -0.15
    ardy
    -0.14
    èħIJ
    -0.14
    WN
    -0.14
    gorith
    -0.13
     Mori
    -0.13
    تص
    -0.13
    ifar
    -0.13
     Inflate
    -0.13
    POSITIVE LOGITS
    ovich
    0.16
    داÙħ
    0.14
    rick
    0.14
    won
    0.14
    elson
    0.14
    idges
    0.14
     unregister
    0.14
    urn
    0.14
    ers
    0.13
    stead
    0.13
    Activations Density 0.036%

    No Known Activations