© 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. 92158
    Prev
    Next
    INDEX
    Explanations

    mentions of news outlets or reporting entities

    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
    ãĤ¤ãĤº
    -0.07
    emean
    -0.07
    à¹Ģล
    -0.06
    ấn
    -0.06
    lav
    -0.06
    inson
    -0.06
    cot
    -0.06
    assador
    -0.06
    cts
    -0.06
    estroy
    -0.06
    POSITIVE LOGITS
    ustil
    0.06
     previously
    0.06
    jax
    0.06
    wert
    0.06
    ryn
    0.06
    _requests
    0.06
     omas
    0.06
     Shut
    0.06
    abe
    0.06
    км
    0.06
    Activations Density 0.009%

    No Known Activations