© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87610
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements in code, particularly related to function calls and statements

    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
    ocator
    -0.08
    kup
    -0.08
    idon
    -0.08
    Ñĥнк
    -0.08
    idges
    -0.07
    ÑĪин
    -0.07
    berman
    -0.07
    phinx
    -0.07
    hiba
    -0.07
    _RB
    -0.07
    POSITIVE LOGITS
     Quentin
    0.06
    iat
    0.06
     Song
    0.05
    ones
    0.05
     specialty
    0.05
     III
    0.05
     Marilyn
    0.05
    ful
    0.05
     Kit
    0.05
    oro
    0.05
    Activations Density 0.003%

    No Known Activations