© 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. 22-LLAMASCOPE-RES-131K
    11. 4179
    Prev
    Next
    INDEX
    Explanations

    fractions and ratios related to statistics or demographics

    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
    åĿĬ
    -0.07
    .precision
    -0.07
    zek
    -0.07
    hack
    -0.07
    Äħż
    -0.06
    oons
    -0.06
    ibur
    -0.06
    оÑĢоÑĪ
    -0.06
    umps
    -0.06
    oops
    -0.06
    POSITIVE LOGITS
    roller
    0.07
    733
    0.07
    fone
    0.06
    conc
    0.06
    /Dk
    0.06
    ny
    0.06
    adir
    0.06
    vince
    0.05
    _iff
    0.05
    der
    0.05
    Activations Density 0.008%

    No Known Activations