© 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. 62223
    Prev
    Next
    INDEX
    Explanations

    technical components and mechanisms related to machinery or devices

    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
     zel
    -0.07
    354
    -0.06
    aida
    -0.06
    ëłµ
    -0.06
     indeed
    -0.06
     fancy
    -0.06
     verg
    -0.06
    ĥ
    -0.06
    quote
    -0.06
    idot
    -0.06
    POSITIVE LOGITS
     mechanism
    0.09
     Äijá»ĥ
    0.08
     ÑĩÑĤобÑĭ
    0.08
     Ñīоб
    0.07
     afin
    0.07
     Authentic
    0.07
    esktop
    0.06
     Möglichkeit
    0.06
    ìĦĿ
    0.06
    NotFoundError
    0.06
    Activations Density 0.050%

    No Known Activations