© 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. 3242
    Prev
    Next
    INDEX
    Explanations

    verbs indicating significant events or actions

    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
    /respond
    -0.08
    oÅĻ
    -0.06
     Erotik
    -0.06
    δο
    -0.06
     veget
    -0.06
     moci
    -0.06
    .invoke
    -0.06
     вк
    -0.06
    IBUTES
    -0.06
    aks
    -0.06
    POSITIVE LOGITS
    asyarak
    0.07
    ovy
    0.07
    erli
    0.06
     tw
    0.06
     publication
    0.06
     toward
    0.06
     towards
    0.06
     allowing
    0.06
    rov
    0.06
     realizing
    0.06
    Activations Density 0.019%

    No Known Activations