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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-LLAMASCOPE-RES-32K
    6. 13389
    Prev
    Next
    INDEX
    Explanations

    references to time periods and projections related to emissions or production data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    encil
    -0.15
     Portions
    -0.15
     Julian
    -0.14
    antry
    -0.14
    otos
    -0.14
    ewe
    -0.14
    /lg
    -0.14
     Pav
    -0.13
     wich
    -0.13
    inges
    -0.13
    POSITIVE LOGITS
    legg
    0.17
    apiro
    0.16
    asser
    0.16
    mate
    0.16
    aire
    0.14
     gamm
    0.14
    zer
    0.14
     Cassidy
    0.14
    ada
    0.14
    YP
    0.14
    Activations Density 0.334%

    No Known Activations