© 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. 5-LLAMASCOPE-RES-131K
    11. 126052
    Prev
    Next
    INDEX
    Explanations

    references to geographical or protected 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
    rit
    -0.07
     Floating
    -0.06
     Ud
    -0.06
    nam
    -0.06
    rita
    -0.06
    Floating
    -0.06
    rias
    -0.06
    ald
    -0.06
    inic
    -0.06
     Lester
    -0.06
    POSITIVE LOGITS
    zew
    0.08
    iffs
    0.08
    icari
    0.07
    -toggler
    0.07
    lege
    0.07
    locator
    0.07
    bÃŃ
    0.07
    coles
    0.06
    vana
    0.06
    vell
    0.06
    Activations Density 0.000%

    No Known Activations