© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 128325
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Dock" and related terms

    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
    antz
    -0.08
    _DM
    -0.08
    Ỽ
    -0.08
    ccione
    -0.07
    rices
    -0.07
    ÙĦÛĮت
    -0.07
    vro
    -0.07
    udit
    -0.07
    .refs
    -0.07
    ERTICAL
    -0.07
    POSITIVE LOGITS
    yard
    0.09
    efeller
    0.08
    yards
    0.07
    enzie
    0.07
    tail
    0.07
    erty
    0.07
    ford
    0.06
    ings
    0.06
    ets
    0.06
    side
    0.06
    Activations Density 0.005%

    No Known Activations