© 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. 55864
    Prev
    Next
    INDEX
    Explanations

    geopolitical entities or locations

    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
    arning
    -0.07
    rend
    -0.06
     seriousness
    -0.06
    ranking
    -0.06
    ICC
    -0.06
    acas
    -0.06
     наÑģÑĤÑĥп
    -0.06
    bedo
    -0.06
     dicks
    -0.06
    oton
    -0.06
    POSITIVE LOGITS
     misc
    0.07
     Misc
    0.07
    rut
    0.06
     including
    0.06
    raquo
    0.06
    éĻIJ
    0.06
    Misc
    0.06
     Vic
    0.06
    ä»ĺ
    0.06
     dissert
    0.06
    Activations Density 0.003%

    No Known Activations