© 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. 75248
    Prev
    Next
    INDEX
    Explanations

    references to using hands and utensils in cooking instructions

    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
    alon
    -0.08
    tridge
    -0.08
    arro
    -0.08
     nackt
    -0.07
    anke
    -0.07
    amet
    -0.07
    alysis
    -0.07
     Æ°Æ¡ng
    -0.07
     badges
    -0.07
    kich
    -0.07
    POSITIVE LOGITS
    uman
    0.06
    erna
    0.06
     rig
    0.06
     shovel
    0.06
     electric
    0.06
     Charg
    0.06
     Ab
    0.06
     resmi
    0.06
     charged
    0.06
     hand
    0.06
    Activations Density 0.014%

    No Known Activations