© 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. 28315
    Prev
    Next
    INDEX
    Explanations

    terms related to legal disclaimers and warranties

    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
    ãĤŃãĥ¥
    -0.07
    ctest
    -0.07
    .ExecuteScalar
    -0.07
    angen
    -0.07
    иÑĤов
    -0.06
    iline
    -0.06
    endregion
    -0.06
    pagen
    -0.06
    lsi
    -0.06
    _LOOKUP
    -0.06
    POSITIVE LOGITS
    adlo
    0.06
     Fle
    0.06
     cita
    0.06
    åķ¦
    0.06
    enis
    0.06
     Sheridan
    0.06
    ously
    0.06
    fest
    0.06
     grounds
    0.06
    Ñıд
    0.05
    Activations Density 0.001%

    No Known Activations