© 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. 118495
    Prev
    Next
    INDEX
    Explanations

    mentions of videos

    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
    /downloads
    -0.07
    esser
    -0.06
    616
    -0.06
    924
    -0.06
     inn
    -0.06
    opause
    -0.06
    line
    -0.06
    oma
    -0.06
     line
    -0.05
    ocol
    -0.05
    POSITIVE LOGITS
     offsetof
    0.08
    å¼ı
    0.07
    à¸ŀร
    0.07
    tür
    0.07
    ForResult
    0.07
     Fant
    0.07
    apore
    0.07
    Verb
    0.07
    /print
    0.07
    stp
    0.07
    Activations Density 0.020%

    No Known Activations