© 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. 76276
    Prev
    Next
    INDEX
    Explanations

    phrases related to events and performances

    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
    atif
    -0.07
     kterým
    -0.07
    иÑī
    -0.07
    =".$_
    -0.06
    ãĥ¡ãĥ©
    -0.06
    idl
    -0.06
    ầy
    -0.06
    etzt
    -0.06
    Malloc
    -0.06
    ãģĦãģĨ
    -0.06
    POSITIVE LOGITS
     various
    0.13
    åIJĦç§į
    0.09
     Various
    0.09
    Various
    0.09
     ÑĢазлиÑĩнÑĭÑħ
    0.09
    /by
    0.08
     verschied
    0.07
    åIJĦ
    0.07
    ÃľM
    0.07
     variety
    0.07
    Activations Density 0.034%

    No Known Activations