Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96206
    Prev
    Next
    INDEX
    Explanations

    references to legislative bills and transportation routes

    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
    кÑĥÑĢ
    -0.07
    CTX
    -0.06
    á»ĵng
    -0.06
    _micro
    -0.06
    ereco
    -0.06
    inverse
    -0.06
    ĨĴ
    -0.06
    endas
    -0.06
    .gg
    -0.06
    rien
    -0.06
    POSITIVE LOGITS
    fulness
    0.07
    sson
    0.06
     Weiss
    0.06
    Ïĥί
    0.06
    460
    0.06
    swith
    0.06
    Ñİ
    0.06
     Historical
    0.06
    (s
    0.06
    bers
    0.06
    Activations Density 0.005%

    No Known Activations