© 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. 106419
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal issues and their implications

    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
    aga
    -0.07
    away
    -0.06
    orta
    -0.06
    iosper
    -0.06
    iffer
    -0.06
    570
    -0.06
     Me
    -0.06
     away
    -0.06
     wit
    -0.06
     Prov
    -0.05
    POSITIVE LOGITS
    metatable
    0.07
    ErrorException
    0.07
    513
    0.07
    šak
    0.07
    akat
    0.07
    starter
    0.07
    ALLERY
    0.07
    touches
    0.06
     ÏĦÏīν
    0.06
     cá»§a
    0.06
    Activations Density 0.071%

    No Known Activations