© 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. 128869
    Prev
    Next
    INDEX
    Explanations

    expressions indicating interest or involvement in various activities or subjects

    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
    üstü
    -0.07
    etak
    -0.06
    odash
    -0.06
    aras
    -0.06
     Masc
    -0.06
    ulas
    -0.06
    è±
    -0.06
    ustil
    -0.06
    æ
    -0.06
    unts
    -0.06
    POSITIVE LOGITS
     habit
    0.09
     trouble
    0.08
     organ
    0.08
    leigh
    0.08
    abit
    0.07
     Trouble
    0.07
    ymm
    0.07
     habits
    0.07
    ONTAL
    0.07
     mess
    0.07
    Activations Density 0.015%

    No Known Activations