Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106541
    Prev
    Next
    INDEX
    Explanations

    the presence and variation of the word "use" in different contexts related to programming or function definitions

    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
    ness
    -0.08
    .au
    -0.07
    ervice
    -0.07
    loe
    -0.07
    adj
    -0.07
    sdale
    -0.07
    .gdx
    -0.06
    ton
    -0.06
    shot
    -0.06
    lo
    -0.06
    POSITIVE LOGITS
    ful
    0.10
    able
    0.09
    age
    0.09
    conds
    0.08
    fulness
    0.08
    ownik
    0.08
    itia
    0.07
    FUL
    0.07
    full
    0.07
    psilon
    0.07
    Activations Density 0.007%

    No Known Activations