© 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. 15-LLAMASCOPE-RES-131K
    11. 807
    Prev
    Next
    INDEX
    Explanations

    specific legal and investigative terminology related to rare cases and medical 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
    ihad
    -0.07
    ensem
    -0.07
    iverse
    -0.07
    (æĹ¥
    -0.07
    ản
    -0.07
    //-
    -0.06
    enson
    -0.06
    ocr
    -0.06
     Patterson
    -0.06
     dna
    -0.06
    POSITIVE LOGITS
     typically
    0.09
     normally
    0.09
     commonly
    0.08
     usually
    0.08
     Normally
    0.08
     rarity
    0.08
     typical
    0.08
     generally
    0.08
     Commonwealth
    0.07
     common
    0.07
    Activations Density 0.036%

    No Known Activations