© 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. 40655
    Prev
    Next
    INDEX
    Explanations

    interactions and actions involving groups and their dynamics

    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
    yre
    -0.07
    ÅĻet
    -0.07
     ViewGroup
    -0.06
     Mex
    -0.06
    DNS
    -0.06
     Voor
    -0.06
    ihat
    -0.06
    776
    -0.06
    ihad
    -0.06
     ÐIJлекÑģанд
    -0.06
    POSITIVE LOGITS
     English
    0.08
    hurst
    0.07
    English
    0.07
    portun
    0.06
     english
    0.06
     ìĺģìĸ´
    0.06
    èĭ±è¯Ń
    0.06
     untranslated
    0.06
    ende
    0.06
     communic
    0.06
    Activations Density 0.019%

    No Known Activations