© 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. 87476
    Prev
    Next
    INDEX
    Explanations

    references to actions that require authorization or permission

    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
    adena
    -0.06
    abella
    -0.06
    ìĹŃ
    -0.06
    elman
    -0.06
    yla
    -0.06
    noun
    -0.06
    emma
    -0.06
    λι
    -0.06
     Lust
    -0.06
    Ñĥда
    -0.05
    POSITIVE LOGITS
    orida
    0.07
    ìĿ´ëĵľ
    0.07
    rowned
    0.07
     legality
    0.07
    iationException
    0.06
    TION
    0.06
    èĥİ
    0.06
    /xhtml
    0.06
    OE
    0.06
    جÙĪÛĮ
    0.06
    Activations Density 0.000%

    No Known Activations