© 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. 2256
    Prev
    Next
    INDEX
    Explanations

    advantages and disadvantages in a comparison context

    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
    ulp
    -0.07
    aub
    -0.07
    Ñĩе
    -0.06
    -pin
    -0.06
    nock
    -0.06
    ĤŃ
    -0.06
    _flg
    -0.06
    iants
    -0.06
     Corpus
    -0.06
    tom
    -0.06
    POSITIVE LOGITS
    eatures
    0.07
    umba
    0.07
    otte
    0.07
    kp
    0.06
    APPER
    0.06
     aspect
    0.06
    ford
    0.06
     Ridley
    0.06
     Aspect
    0.06
     nice
    0.06
    Activations Density 0.004%

    No Known Activations