© 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. 15-LLAMASCOPE-RES-131K
    11. 103932
    Prev
    Next
    INDEX
    Explanations

    references to social connections and gatherings

    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
    angler
    -0.07
    utow
    -0.07
    itsu
    -0.07
    ogui
    -0.07
    ansk
    -0.07
    _DEAD
    -0.07
    279
    -0.07
    ague
    -0.06
    izon
    -0.06
    inski
    -0.06
    POSITIVE LOGITS
     friends
    0.09
     invited
    0.07
     invite
    0.07
    ovation
    0.07
     friend
    0.06
     impunity
    0.06
     gathered
    0.06
     invitation
    0.06
     amigos
    0.06
     Jud
    0.06
    Activations Density 0.019%

    No Known Activations