© 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. 40813
    Prev
    Next
    INDEX
    Explanations

    specific terms related to user interface elements and contact management

    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
     ðŁĺī↵↵
    -0.06
    InProgress
    -0.06
    Screenshot
    -0.06
    ench
    -0.06
    bat
    -0.06
    ÌĨ
    -0.06
    .pretty
    -0.06
    unsubscribe
    -0.06
     prelim
    -0.06
    usa
    -0.06
    POSITIVE LOGITS
    âĢı
    0.07
    elor
    0.06
    .qq
    0.06
    Argb
    0.06
     peÅŁ
    0.06
    νομ
    0.06
    _DEPRECATED
    0.06
    marvin
    0.06
    âĢİ
    0.06
     Jennings
    0.06
    Activations Density 0.069%

    No Known Activations