© 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. 95250
    Prev
    Next
    INDEX
    Explanations

    specific titles or keywords associated with creative or critical storytelling in various 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
    ÑįÑĤ
    -0.07
    ãĥĵãĥ¼
    -0.07
    acob
    -0.07
    formace
    -0.07
    .Middle
    -0.07
    梨
    -0.07
    ÏĦικο
    -0.07
    ÑĢÑĸÑı
    -0.07
    .getElements
    -0.07
    .UIManager
    -0.07
    POSITIVE LOGITS
    ’s
    0.07
     Magazine
    0.07
    ®
    0.07
     Flesh
    0.06
    ®,
    0.06
    -sponsored
    0.06
    ibold
    0.06
    -logo
    0.06
    logo
    0.06
    ieber
    0.06
    Activations Density 0.143%

    No Known Activations