© 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. 60633
    Prev
    Next
    INDEX
    Explanations

    names or titles associated with people or specific roles

    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
    emotion
    -0.09
    nelly
    -0.09
    emek
    -0.07
    hrad
    -0.07
    dued
    -0.07
    nad
    -0.07
    Äįné
    -0.07
    swick
    -0.07
    Beam
    -0.07
    trys
    -0.07
    POSITIVE LOGITS
     Gavin
    0.06
     cons
    0.06
     pá
    0.05
     exh
    0.05
    icopt
    0.05
     Schwarz
    0.05
    404
    0.05
     Uncategorized
    0.05
    paced
    0.05
    641
    0.05
    Activations Density 0.024%

    No Known Activations