© 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. 31-LLAMASCOPE-RES-32K
    11. 18476
    Prev
    Next
    INDEX
    Explanations

    references to the color black and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ics
    -0.69
    ison
    -0.43
    als
    -0.39
    hawks
    -0.39
    burn
    -0.39
    agascar
    -0.39
    mund
    -0.38
    win
    -0.38
    ropolitan
    -0.38
    ational
    -0.37
    POSITIVE LOGITS
    ges
    0.17
    abilities
    0.17
    urry
    0.16
    rani
    0.15
     minded
    0.15
    rub
    0.15
    ight
    0.14
    puted
    0.14
    leen
    0.14
     Flake
    0.14
    Activations Density 0.054%

    No Known Activations