© 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. 103594
    Prev
    Next
    INDEX
    Explanations

    phrases related to reporting and commentary

    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
    iras
    -0.08
    ippet
    -0.07
    obia
    -0.06
    ubat
    -0.06
     bruk
    -0.06
    nej
    -0.06
    mtx
    -0.06
    ilos
    -0.06
    iationException
    -0.06
    legate
    -0.06
    POSITIVE LOGITS
    ()",
    0.06
    cher
    0.06
    fx
    0.06
     himself
    0.06
    ",
    0.06
     ther
    0.06
    ?type
    0.06
     geçen
    0.06
    ãĢij,
    0.06
    \",
    0.06
    Activations Density 0.014%

    No Known Activations