© 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. 75174
    Prev
    Next
    INDEX
    Explanations

    phrases related to population size and city rankings

    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
     Phon
    -0.07
    reater
    -0.06
     external
    -0.06
     External
    -0.06
     local
    -0.06
    ippi
    -0.06
     phon
    -0.06
    ragen
    -0.05
    efon
    -0.05
    cker
    -0.05
    POSITIVE LOGITS
    oton
    0.08
    disp
    0.07
    sand
    0.07
    £¼
    0.07
    Å¡ek
    0.07
    tright
    0.07
    ëħķ
    0.07
    sko
    0.06
    hrad
    0.06
     Sung
    0.06
    Activations Density 0.004%

    No Known Activations