© 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. 16603
    Prev
    Next
    INDEX
    Explanations

    references to activities or engagement in various contexts

    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
    arton
    -0.07
    ayd
    -0.07
     knull
    -0.07
    (||
    -0.07
    sip
    -0.07
    znik
    -0.07
    便
    -0.07
    .toolbox
    -0.06
    kea
    -0.06
     duk
    -0.06
    POSITIVE LOGITS
    icro
    0.06
     activity
    0.06
    elow
    0.06
     trot
    0.06
    pras
    0.06
    0.06
    irit
    0.06
    nak
    0.06
     Activity
    0.06
    Activity
    0.06
    Activations Density 0.004%

    No Known Activations