© 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. 22-LLAMASCOPE-RES-131K
    11. 4110
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of inadequacy or dissatisfaction

    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
    _REQUIRED
    -0.07
    ote
    -0.07
     Dating
    -0.06
    chw
    -0.06
    ContextMenu
    -0.06
    ãģ®ä¸Ĭ
    -0.06
    prene
    -0.06
     Unsupported
    -0.05
    _blocking
    -0.05
    ä¸į足
    -0.05
    POSITIVE LOGITS
    immers
    0.07
    alars
    0.07
     forthcoming
    0.07
     working
    0.07
    awks
    0.06
    Leod
    0.06
    ENA
    0.06
    ibold
    0.06
     Dere
    0.06
     right
    0.06
    Activations Density 0.025%

    No Known Activations