© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 87376
    Prev
    Next
    INDEX
    Explanations

    references to statements and their consistency or inconsistency

    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
    attice
    -0.06
    okes
    -0.06
     Rough
    -0.06
    ιÏĩ
    -0.06
     SHALL
    -0.06
    elia
    -0.06
    SDL
    -0.06
    λÏĮγ
    -0.05
    RIA
    -0.05
     comp
    -0.05
    POSITIVE LOGITS
     nowhere
    0.12
     actually
    0.09
     did
    0.09
     merely
    0.08
     statement
    0.07
     precisely
    0.07
    ãģ£ãģį
    0.07
    uml
    0.07
     never
    0.07
    statement
    0.07
    Activations Density 0.046%

    No Known Activations