© 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. 9-LLAMASCOPE-RES-131K
    11. 94677
    Prev
    Next
    INDEX
    Explanations

    elements of code structure and control flow

    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
    uled
    -0.06
    ضع
    -0.06
    serter
    -0.06
     candidate
    -0.06
    ndo
    -0.06
    antis
    -0.06
    rush
    -0.06
    ählen
    -0.06
    ngine
    -0.06
    .DropTable
    -0.06
    POSITIVE LOGITS
     Mandal
    0.07
    _partner
    0.07
    eut
    0.07
     Sanayi
    0.06
    .SDK
    0.06
     âĨij
    0.06
    ë¹
    0.06
    ãĥ¼ãĥį
    0.06
    hetto
    0.06
    å®ı
    0.06
    Activations Density 0.014%

    No Known Activations