© 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. 78836
    Prev
    Next
    INDEX
    Explanations

    header-related elements in programming or data structures

    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
     tw
    -0.07
     cond
    -0.05
     co
    -0.05
     ins
    -0.05
     exp
    -0.05
    185
    -0.05
     a
    -0.05
     e
    -0.05
     n
    -0.05
    ÑħÑĥ
    -0.05
    POSITIVE LOGITS
     nameof
    0.09
    posables
    0.08
    ifecycle
    0.08
    evice
    0.08
    removeAttr
    0.08
     forKey
    0.07
    'gc
    0.07
    _constants
    0.07
    metatable
    0.07
    endum
    0.07
    Activations Density 0.044%

    No Known Activations