© 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. 60790
    Prev
    Next
    INDEX
    Explanations

    updates or changes in news articles and reports

    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
    ulan
    -0.06
    ophil
    -0.06
    vents
    -0.06
    ová
    -0.06
    itore
    -0.06
     aqu
    -0.06
    quir
    -0.06
     Aqu
    -0.05
    bole
    -0.05
     anthrop
    -0.05
    POSITIVE LOGITS
    æŁ´
    0.06
    ked
    0.06
    Ñĸж
    0.06
    TED
    0.06
    _totals
    0.06
     باع
    0.06
    ÏģÏī
    0.06
    svp
    0.06
    Unicode
    0.06
    PCM
    0.06
    Activations Density 0.001%

    No Known Activations