© 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. 16824
    Prev
    Next
    INDEX
    Explanations

    numerical rankings or positions related to geographical or demographic references

    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
    azon
    -0.06
    acionales
    -0.06
     Dependencies
    -0.06
    py
    -0.06
     Dependency
    -0.06
    owell
    -0.06
     intermedi
    -0.06
    -o
    -0.05
    etter
    -0.05
     éĸ¢
    -0.05
    POSITIVE LOGITS
    第ä¸ī
    0.07
    AINS
    0.07
    सन
    0.07
    éĢ
    0.07
    ẫn
    0.07
    omorphic
    0.07
    á»ĵ
    0.07
    strcasecmp
    0.07
    вÑĢоп
    0.07
    enÃŃ
    0.07
    Activations Density 0.018%

    No Known Activations