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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 117222
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a direction or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hta
    -0.07
    orf
    -0.06
    apesh
    -0.06
    appid
    -0.06
    caf
    -0.06
    uv
    -0.06
    .onStart
    -0.06
     Offensive
    -0.06
    ัย
    -0.06
    us
    -0.06
    POSITIVE LOGITS
    ÑĢÑĥн
    0.07
    SWG
    0.07
    YPRE
    0.07
    pj
    0.07
    ether
    0.06
    riterion
    0.06
    Projected
    0.06
    lsi
    0.06
    JKLM
    0.06
    unsch
    0.06
    Activations Density 0.028%

    No Known Activations