© 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. 15-LLAMASCOPE-RES-131K
    6. 803
    Prev
    Next
    INDEX
    Explanations

    occurrences of import statements and references to packages in code

    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
    atron
    -0.07
    prü
    -0.06
    rones
    -0.06
    parms
    -0.06
    ëĿ¼ëıĦ
    -0.06
    ParseException
    -0.06
    odom
    -0.06
    Typed
    -0.06
    DataContract
    -0.06
    ooting
    -0.06
    POSITIVE LOGITS
    anson
    0.07
     Blowjob
    0.06
    cheid
    0.06
     Einsatz
    0.06
    endir
    0.06
     ours
    0.06
    ornings
    0.06
    atre
    0.06
    .cent
    0.06
     راÙĩ
    0.06
    Activations Density 0.002%

    No Known Activations