© 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. 17-LLAMASCOPE-RES-131K
    11. 94118
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditionality or uncertainty

    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
    Trivia
    -0.07
    zem
    -0.07
    iler
    -0.07
    ãģ«ãĤĤ
    -0.07
     Vaults
    -0.07
    ancellationToken
    -0.07
    CLS
    -0.07
    Ỽp
    -0.07
    @nate
    -0.07
    .cod
    -0.07
    POSITIVE LOGITS
     Or
    0.14
     atleast
    0.13
     or
    0.13
     least
    0.13
    Or
    0.11
    èĩ³å°ij
    0.11
    Except
    0.10
     except
    0.10
    -or
    0.10
     Except
    0.10
    Activations Density 0.130%

    No Known Activations