© 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. 40685
    Prev
    Next
    INDEX
    Explanations

    links and resources related to programming or software development

    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
    itler
    -0.07
    lbrakk
    -0.07
    argin
    -0.06
     PRES
    -0.06
    IGH
    -0.06
     slee
    -0.06
    overs
    -0.06
    erca
    -0.06
     pres
    -0.06
     Pres
    -0.06
    POSITIVE LOGITS
    ois
    0.06
    ocs
    0.06
     tag
    0.06
    immutable
    0.06
    .semantic
    0.06
     éĽ
    0.06
     SOS
    0.06
    okoj
    0.06
     Crown
    0.06
     oprav
    0.06
    Activations Density 0.002%

    No Known Activations