© 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. 41974
    Prev
    Next
    INDEX
    Explanations

    references to contracts and agreements

    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
    icus
    -0.07
    folio
    -0.07
     redundancy
    -0.07
    ازÛĮ
    -0.07
    fi
    -0.07
    vecs
    -0.07
    evin
    -0.07
    quette
    -0.06
    orgot
    -0.06
    æķĪ
    -0.06
    POSITIVE LOGITS
     award
    0.07
    Descriptors
    0.06
     awarded
    0.06
     shr
    0.06
    .wrap
    0.06
     ye
    0.06
    mile
    0.06
     μÎŃÏģοÏĤ
    0.06
     gut
    0.06
    lap
    0.05
    Activations Density 0.000%

    No Known Activations