© 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 EvalsExportsAPI 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. 86176
    Prev
    Next
    INDEX
    Explanations

    geographical locations and institutions

    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
    rega
    -0.08
    aders
    -0.07
    Ñıж
    -0.07
    etheless
    -0.06
    MethodImpl
    -0.06
    apore
    -0.06
    amics
    -0.06
    rew
    -0.06
    ill
    -0.06
    REW
    -0.06
    POSITIVE LOGITS
    -based
    0.08
    _cre
    0.08
     branch
    0.08
    ernal
    0.07
     edition
    0.07
     Office
    0.07
     Association
    0.07
     clearing
    0.06
     preval
    0.06
     chapter
    0.06
    Activations Density 0.075%

    No Known Activations