© 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. 30324
    Prev
    Next
    INDEX
    Explanations

    numerical values or specific identifiers related to dates, measurements, or statistics

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

    Chronologically organized content items in structured formats, particularly employment histories, publication dates, or content listings on websites and databases.

    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
    olas
    -0.07
    appa
    -0.06
    pec
    -0.06
    ering
    -0.06
    ÅĻ
    -0.06
    apa
    -0.06
    cale
    -0.06
    ama
    -0.06
     instead
    -0.06
    jected
    -0.06
    POSITIVE LOGITS
    -LAST
    0.09
    _EDEFAULT
    0.07
    actionDate
    0.07
    ï½į
    0.07
    .bytes
    0.07
    ãİ
    0.07
    _tC
    0.07
    (åľŁ
    0.07
    \OptionsResolver
    0.06
    erdem
    0.06
    Activations Density 0.047%

    No Known Activations