© 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. 15-LLAMASCOPE-RES-131K
    11. 790
    Prev
    Next
    INDEX
    Explanations

    references to community events and gatherings

    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
    権
    -0.07
    éĺħ读次æķ°
    -0.07
     ЧаÑģ
    -0.07
    kara
    -0.07
    .walk
    -0.07
    JECTION
    -0.06
    дон
    -0.06
     erotik
    -0.06
    anders
    -0.06
    ãĥ¬ãĤ¹
    -0.06
    POSITIVE LOGITS
     representatives
    0.07
    0.07
     representative
    0.06
    852
    0.06
    835
    0.06
    gew
    0.06
     phil
    0.06
     recorder
    0.05
     Recorder
    0.05
     hay
    0.05
    Activations Density 0.020%

    No Known Activations