© 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. 126981
    Prev
    Next
    INDEX
    Explanations

    the word "but."

    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
    λλη
    -0.06
    owski
    -0.06
    mez
    -0.06
    348
    -0.06
     kalan
    -0.06
    /browse
    -0.06
    394
    -0.06
     Platt
    -0.06
    RLF
    -0.06
    Ùĭا
    -0.06
    POSITIVE LOGITS
    -addons
    0.07
    elop
    0.07
     пÑĢоз
    0.07
    assage
    0.07
    attles
    0.07
    isté
    0.07
    instead
    0.07
    aux
    0.07
    aña
    0.07
    èŃľ
    0.07
    Activations Density 0.000%

    No Known Activations