© 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. 3930
    Prev
    Next
    INDEX
    Explanations

    references to news events or updates

    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
    ito
    -0.06
    ols
    -0.06
    ing
    -0.06
     summar
    -0.06
    è·
    -0.06
     issues
    -0.06
    ates
    -0.05
    ictor
    -0.05
    (s
    -0.05
    666
    -0.05
    POSITIVE LOGITS
    .fm
    0.08
    abyrin
    0.08
    Sharper
    0.08
     bahwa
    0.08
    eled
    0.08
    agli
    0.08
    ]={↵
    0.08
    anie
    0.08
    oldur
    0.07
     news
    0.07
    Activations Density 0.012%

    No Known Activations