© 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. 57689
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and emotional transitions

    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
     normal
    -0.07
    ensure
    -0.07
     ensure
    -0.07
    odore
    -0.06
    Ø¡
    -0.06
     sanit
    -0.06
    -G
    -0.06
     Ensure
    -0.06
     tips
    -0.06
     officials
    -0.05
    POSITIVE LOGITS
    ÄĽr
    0.08
     ::::::::
    0.08
    álo
    0.07
    FRING
    0.07
    sein
    0.07
    PROTO
    0.07
    gest
    0.07
    ukan
    0.07
    ÄĽle
    0.07
    experimental
    0.07
    Activations Density 0.022%

    No Known Activations