© 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. 2-LLAMASCOPE-RES-32K
    11. 28302
    Prev
    Next
    INDEX
    Explanations

    numerical data, specifically statistics related to game performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    om
    -0.15
    禮
    -0.14
    ún
    -0.14
    óm
    -0.14
     oy
    -0.14
    236
    -0.13
    ì²´
    -0.13
    ervers
    -0.13
     unf
    -0.13
    ®
    -0.13
    POSITIVE LOGITS
    eken
    0.17
    istle
    0.15
    alte
    0.15
    ÑıÑĩи
    0.14
    icana
    0.14
    endoza
    0.14
    idend
    0.14
    isms
    0.14
     nhánh
    0.14
    ROL
    0.14
    Activations Density 0.023%

    No Known Activations