© 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. 57075
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of community or collective experience

    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¸Ģ人
    -0.06
    966
    -0.06
     itself
    -0.06
    ena
    -0.06
     ============================================================================↵
    -0.06
     nackte
    -0.06
    å¸Ń
    -0.06
     stuff
    -0.06
    au
    -0.05
    oxy
    -0.05
    POSITIVE LOGITS
    ewis
    0.08
    abbo
    0.07
    è³¢
    0.07
    luv
    0.07
    ITIONAL
    0.07
    .crt
    0.07
    366
    0.06
    asons
    0.06
    lobal
    0.06
    ardu
    0.06
    Activations Density 0.009%

    No Known Activations