© 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. 83271
    Prev
    Next
    INDEX
    Explanations

    occurrences of articles and prepositions related to location

    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
    LOPT
    -0.07
    erif
    -0.07
    umbn
    -0.07
    orton
    -0.07
    acle
    -0.06
    ä¿Ĭ
    -0.06
     rough
    -0.06
    uner
    -0.06
     μÎŃ
    -0.06
    akis
    -0.06
    POSITIVE LOGITS
     Hindered
    0.07
     Harper
    0.07
    RESSED
    0.07
    oday
    0.07
    ÙĪئ
    0.06
     newspapers
    0.06
    LETTE
    0.06
    วà¸ĩ
    0.06
    imer
    0.06
    adia
    0.06
    Activations Density 0.017%

    No Known Activations