© 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. 82939
    Prev
    Next
    INDEX
    Explanations

    references to actions, particularly those related to creation or production processes

    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
    .lift
    -0.07
    ierz
    -0.07
    TREE
    -0.06
     stakes
    -0.06
     Dawn
    -0.06
    /Branch
    -0.06
    astery
    -0.06
    iero
    -0.06
    olicy
    -0.06
    ÑĨеп
    -0.06
    POSITIVE LOGITS
    989
    0.07
    .bunifuFlatButton
    0.07
     напÑĢи
    0.07
    ellan
    0.07
    ocab
    0.07
    uble
    0.07
    asca
    0.06
    81
    0.06
    954
    0.06
     conducted
    0.06
    Activations Density 0.026%

    No Known Activations