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. 9-LLAMASCOPE-RES-32K
    6. 20837
    Prev
    Next
    INDEX
    Explanations

    commas and various types of names or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pond
    -0.15
    asley
    -0.14
    lap
    -0.14
    огод
    -0.14
     Lane
    -0.14
    _terms
    -0.13
    lo
    -0.13
     Dag
    -0.13
    ernes
    -0.13
    αÏĥ
    -0.13
    POSITIVE LOGITS
    /TT
    0.15
    idos
    0.15
    uhe
    0.15
    ologi
    0.14
    osten
    0.14
    ervas
    0.14
    ££
    0.14
    nel
    0.13
    alnız
    0.13
    eriod
    0.13
    Activations Density 0.016%

    No Known Activations