© 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. 108022
    Prev
    Next
    INDEX
    Explanations

    references to analytics, data, or reports, particularly in the context of security and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Proper nouns representing names of people, places, organizations, or specialized technical terms appearing in various contextual settings.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    odore
    -0.11
    pper
    -0.08
    ering
    -0.08
    oner
    -0.08
    |array
    -0.08
    arton
    -0.08
    erable
    -0.07
    çİĩ
    -0.07
    ảo
    -0.07
    ÑģÑı
    -0.07
    POSITIVE LOGITS
    buquerque
    0.09
    assador
    0.08
    itr
    0.08
    waves
    0.08
    ended
    0.08
    elaide
    0.07
    quivos
    0.07
    .BASELINE
    0.07
    ethyst
    0.07
    .LEADING
    0.07
    Activations Density 2.848%

    No Known Activations