© 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. 76590
    Prev
    Next
    INDEX
    Explanations

    instances of ellipses or truncated sentences

    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
    egt
    -0.07
    ottie
    -0.06
    Ïģε
    -0.06
    earer
    -0.06
    zt
    -0.06
    egen
    -0.06
    antry
    -0.06
    lix
    -0.06
    áºŃp
    -0.06
    rek
    -0.06
    POSITIVE LOGITS
     IMDb
    0.08
     extras
    0.07
    arel
    0.06
    ìł¤
    0.06
    (es
    0.06
    andy
    0.06
    ancia
    0.06
    _voice
    0.06
    oot
    0.06
    vana
    0.06
    Activations Density 0.000%

    No Known Activations