© 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. 15-LLAMASCOPE-RES-131K
    11. 833
    Prev
    Next
    INDEX
    Explanations

    locations related to Washington, D.C., and notable cities involved in political contexts

    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
     pardon
    -0.06
    REATE
    -0.06
    weise
    -0.06
    oten
    -0.06
     Ari
    -0.06
    apsed
    -0.06
     veto
    -0.06
    rop
    -0.06
    /fl
    -0.06
     Stim
    -0.05
    POSITIVE LOGITS
    OMPI
    0.07
    IRS
    0.07
    inton
    0.07
    ersen
    0.07
    daq
    0.07
    orf
    0.07
     Îķλλην
    0.06
    emm
    0.06
    ån
    0.06
    adians
    0.06
    Activations Density 0.025%

    No Known Activations