© 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. 92871
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "shore" and its variations, indicating a focus on coastal or shoreline contexts

    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
    shaw
    -0.08
    ry
    -0.08
    ruc
    -0.07
    sing
    -0.07
    re
    -0.07
    ово
    -0.07
    zed
    -0.07
    emic
    -0.07
    emp
    -0.07
    éri
    -0.06
    POSITIVE LOGITS
    itution
    0.08
    aders
    0.08
    lines
    0.08
    -side
    0.08
    fills
    0.07
    side
    0.07
    edback
    0.07
    preneur
    0.07
    front
    0.06
    ousel
    0.06
    Activations Density 0.004%

    No Known Activations