© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 41065
    Prev
    Next
    INDEX
    Explanations

    commas or punctuation marks indicating lists or separations

    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
    413
    -0.07
    heim
    -0.07
    ë
    -0.07
     gó
    -0.06
     Vegas
    -0.06
    ÑĸÑĤи
    -0.06
    CLS
    -0.06
    eldig
    -0.06
     Mor
    -0.06
    åĺĽ
    -0.06
    POSITIVE LOGITS
    Æ°a
    0.07
     according
    0.06
    ÐIJÑĢÑħÑĸв
    0.06
    CHANT
    0.06
    /misc
    0.06
    ableObject
    0.06
    BILE
    0.06
    claimer
    0.06
    ifar
    0.06
    á»ijc
    0.06
    Activations Density 0.032%

    No Known Activations