© 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. 120340
    Prev
    Next
    INDEX
    Explanations

    various forms of numerical data and decimal points

    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
    ndern
    -0.07
    atham
    -0.07
    olon
    -0.07
     Rencontre
    -0.07
    asher
    -0.06
    burn
    -0.06
    idian
    -0.06
    _alias
    -0.06
    EMON
    -0.06
    ishment
    -0.06
    POSITIVE LOGITS
    ABB
    0.06
     Cover
    0.06
    ết
    0.06
    osate
    0.06
    Ïħγ
    0.06
    .realm
    0.06
    çĽĸ
    0.06
    ATS
    0.06
    amping
    0.06
    è±
    0.06
    Activations Density 0.007%

    No Known Activations