© 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. 106827
    Prev
    Next
    INDEX
    Explanations

    terms related to significant events or conditions

    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
     heart
    -0.06
     twin
    -0.06
     Bernard
    -0.06
     (
    -0.06
     recent
    -0.06
     uniform
    -0.06
     coc
    -0.06
     Fate
    -0.06
     Inst
    -0.06
     inst
    -0.06
    POSITIVE LOGITS
    ÄĽr
    0.07
    cka
    0.07
    Flush
    0.07
    obel
    0.07
    imler
    0.07
     Erotische
    0.07
     '"';↵
    0.07
    esson
    0.07
    ãĥªãĥ¼
    0.07
    ARIO
    0.07
    Activations Density 0.056%

    No Known Activations