© 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. 128258
    Prev
    Next
    INDEX
    Explanations

    references to various clubs or dining establishments

    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
    sb
    -0.07
    .mybatisplus
    -0.07
    azo
    -0.06
    agu
    -0.06
    egers
    -0.06
    _ENGINE
    -0.06
    raj
    -0.06
    roje
    -0.06
    agina
    -0.06
    yll
    -0.06
    POSITIVE LOGITS
    bing
    0.09
    bers
    0.08
    ystick
    0.07
    bies
    0.07
    esp
    0.07
    809
    0.07
    bable
    0.07
    foot
    0.07
    ndon
    0.07
    tel
    0.07
    Activations Density 0.005%

    No Known Activations