© 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. 5-LLAMASCOPE-RES-131K
    11. 126456
    Prev
    Next
    INDEX
    Explanations

    references to logical conclusions or statements of adherence

    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
    udeau
    -0.07
    sty
    -0.07
    438
    -0.06
    u
    -0.06
    by
    -0.05
    lle
    -0.05
    ullo
    -0.05
     or
    -0.05
    ome
    -0.05
    elli
    -0.05
    POSITIVE LOGITS
    OUN
    0.07
    ately
    0.07
    ιαν
    0.07
    vatel
    0.07
    sız
    0.07
    fern
    0.07
     yerine
    0.07
    evil
    0.07
    acente
    0.07
    .Stretch
    0.07
    Activations Density 0.003%

    No Known Activations