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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77380
    Prev
    Next
    INDEX
    Explanations

    non-standard sentence structures or unique grammatical elements

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

    Programming code sections where quotation marks or message constants are used in string output operations.

    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
    ãĥªãĤ«
    -0.06
    лег
    -0.06
    _HIT
    -0.06
    å¡ļ
    -0.06
    interop
    -0.06
    лова
    -0.06
    onaut
    -0.06
    uitka
    -0.06
     prec
    -0.06
    PARSE
    -0.06
    POSITIVE LOGITS
    ebek
    0.07
    tura
    0.07
    dorf
    0.07
    artz
    0.07
     Marketable
    0.07
    rance
    0.06
    zza
    0.06
     forKey
    0.06
     withObject
    0.06
    agli
    0.06
    Activations Density 0.093%

    No Known Activations