© 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. 74799
    Prev
    Next
    INDEX
    Explanations

    terms related to significant societal issues or themes

    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
    ä¸ĺ
    -0.08
    onga
    -0.08
    atra
    -0.07
    éĻ¢
    -0.07
    veau
    -0.07
    é»ĺ
    -0.06
    ứng
    -0.06
    instanc
    -0.06
    emd
    -0.06
    erva
    -0.06
    POSITIVE LOGITS
     decrement
    0.06
    аÑĢод
    0.06
    سÙħØ©
    0.06
    ola
    0.06
    678
    0.06
    hin
    0.06
    éĹ²
    0.06
    aint
    0.06
    lore
    0.06
    AZY
    0.06
    Activations Density 0.016%

    No Known Activations