© 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. 16640
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations or administrative areas

    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
     Mills
    -0.06
    cio
    -0.06
    OrDefault
    -0.06
    bread
    -0.06
    FC
    -0.06
    tag
    -0.06
    nier
    -0.06
     econ
    -0.06
    us
    -0.06
    .Persistence
    -0.06
    POSITIVE LOGITS
    agal
    0.08
    antino
    0.07
    ntax
    0.07
    VICE
    0.07
    vice
    0.07
    hiba
    0.07
    .Raise
    0.07
    Äı
    0.07
    _tac
    0.06
    ynes
    0.06
    Activations Density 0.000%

    No Known Activations