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. 10-LLAMASCOPE-RES-32K
    6. 13558
    Prev
    Next
    INDEX
    Explanations

    mentions of book titles and their statuses regarding availability or sales

    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
     
    -0.18
     Arn
    -0.16
     dro
    -0.15
     transition
    -0.15
     (
    -0.15
    <|end_of_text|>
    -0.15
     run
    -0.15
     [
    -0.15
    ati
    -0.15
     unders
    -0.14
    POSITIVE LOGITS
    iversit
    0.21
    .mybatisplus
    0.18
    帯
    0.17
    ocre
    0.17
    krv
    0.16
    ROTO
    0.16
    IVO
    0.16
    nothrow
    0.15
    (Parcel
    0.15
    ï¿¥
    0.15
    Activations Density 0.265%

    No Known Activations