Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4359
    Prev
    Next
    INDEX
    Explanations

    references to conductors and musicians in classical music contexts

    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
    inski
    -0.06
     mah
    -0.06
     recursively
    -0.06
    unce
    -0.06
     Herman
    -0.06
    atin
    -0.06
    rement
    -0.06
    ác
    -0.06
    quential
    -0.06
    fec
    -0.05
    POSITIVE LOGITS
     PyErr
    0.07
    dbuf
    0.07
    bote
    0.07
    ledon
    0.07
    tern
    0.07
    *)((
    0.07
    .scalablytyped
    0.07
    ænd
    0.07
     COPYING
    0.07
    ihn
    0.07
    Activations Density 0.012%

    No Known Activations