Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82805
    Prev
    Next
    INDEX
    Explanations

    formatting tags and HTML structure in text

    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
    lesi
    -0.07
    urr
    -0.06
    ker
    -0.06
    ÑĢен
    -0.06
    bis
    -0.06
     Cup
    -0.06
    aus
    -0.06
    _minimum
    -0.06
    lu
    -0.06
    Ñĥда
    -0.06
    POSITIVE LOGITS
    ynes
    0.07
    261
    0.07
    edl
    0.07
    avy
    0.07
    immel
    0.06
    ctors
    0.06
    prung
    0.06
    оÑī
    0.06
    praak
    0.06
    /REC
    0.06
    Activations Density 0.004%

    No Known Activations