© 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. 40179
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Re" or responses indicating reply actions

    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
    azy
    -0.07
    ATEGORIES
    -0.06
    ry
    -0.06
    claimer
    -0.06
    ÑĢоÑģÑĤо
    -0.06
    aepernick
    -0.06
    oten
    -0.06
    POCH
    -0.06
    lie
    -0.06
    awa
    -0.06
    POSITIVE LOGITS
     Bolt
    0.07
    ancode
    0.07
    даÑĤ
    0.06
    umbed
    0.06
    EOS
    0.06
    iever
    0.06
    oreach
    0.06
     Hodg
    0.06
    classed
    0.06
    ï¸ı
    0.06
    Activations Density 0.001%

    No Known Activations