© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 12-LLAMASCOPE-RES-32K
    11. 26004
    Prev
    Next
    INDEX
    Explanations

    content related to corrections and clarifications in articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usc
    -0.17
    ads
    -0.15
     Carry
    -0.14
    un
    -0.14
    azon
    -0.14
    ign
    -0.14
    let
    -0.13
    atches
    -0.13
     progen
    -0.13
    rei
    -0.13
    POSITIVE LOGITS
    ãģ¡ãģ¯
    0.17
    ecute
    0.15
    agma
    0.15
    ิà¸ĸ
    0.15
    frauen
    0.14
    hunter
    0.14
    алеж
    0.14
    anker
    0.14
    usercontent
    0.14
    \Table
    0.14
    Activations Density 0.017%

    No Known Activations