© 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. 119115
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of withdrawal and withdrawal processes

    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
    idl
    -0.07
    emie
    -0.07
    esters
    -0.07
    ERM
    -0.07
    /method
    -0.06
    -ÑĤо
    -0.06
    wig
    -0.06
    allah
    -0.06
    relude
    -0.06
    aque
    -0.06
    POSITIVE LOGITS
    rus
    0.08
    ombat
    0.08
    /loose
    0.07
    orne
    0.07
    ervlet
    0.07
    isper
    0.07
    ables
    0.07
    رÙĪج
    0.07
    soever
    0.06
    icher
    0.06
    Activations Density 0.006%

    No Known Activations