© 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. 9-LLAMASCOPE-RES-131K
    11. 94531
    Prev
    Next
    INDEX
    Explanations

    terms related to agreements and transactions

    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
    ugu
    -0.07
     follower
    -0.07
    nten
    -0.07
    akis
    -0.07
    unami
    -0.07
    followers
    -0.06
    éĻµ
    -0.06
    _ln
    -0.06
    osos
    -0.06
    anten
    -0.06
    POSITIVE LOGITS
     fatt
    0.07
    _firstname
    0.07
    Fold
    0.06
    ádu
    0.06
    ickerView
    0.06
    _OK
    0.06
     ded
    0.06
    aret
    0.06
    .Binding
    0.06
    .ok
    0.06
    Activations Density 0.001%

    No Known Activations