© 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. 78440
    Prev
    Next
    INDEX
    Explanations

    terms related to updates or revisions

    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
    odus
    -0.07
    oulos
    -0.06
    onces
    -0.06
    erland
    -0.06
    .GroupLayout
    -0.06
    _formula
    -0.06
    ARDS
    -0.06
    opr
    -0.06
     deep
    -0.06
    entry
    -0.06
    POSITIVE LOGITS
    -eslint
    0.08
    ObjectContext
    0.07
    ImageContext
    0.07
    createFrom
    0.07
    UGIN
    0.06
    ı
    0.06
     migrationBuilder
    0.06
    avic
    0.06
    +xml
    0.06
     blo
    0.06
    Activations Density 0.000%

    No Known Activations