© 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. 107925
    Prev
    Next
    INDEX
    Explanations

    standardized identifiers related to software or programming

    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
    er
    -0.07
    urr
    -0.06
     Syn
    -0.06
    екÑĤив
    -0.06
    itra
    -0.06
    ivor
    -0.06
    lint
    -0.06
    ht
    -0.06
    Syn
    -0.06
    wner
    -0.06
    POSITIVE LOGITS
    _VERSION
    0.07
    abay
    0.07
     Clyde
    0.07
    алеж
    0.07
    kaç
    0.07
    .mybatisplus
    0.07
    zim
    0.07
    ÙĨز
    0.07
    ylum
    0.06
    (DWORD
    0.06
    Activations Density 0.000%

    No Known Activations