© 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. 75261
    Prev
    Next
    INDEX
    Explanations

    descriptions related to sensory experience, particularly taste and smell

    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
    andes
    -0.07
    igest
    -0.07
    GuidId
    -0.07
    ì¶ľ
    -0.06
     bq
    -0.06
    appen
    -0.06
    áce
    -0.06
    침
    -0.06
    mÃŃn
    -0.06
     Blick
    -0.06
    POSITIVE LOGITS
    verture
    0.08
    rush
    0.07
     expecting
    0.07
    ulen
    0.07
    oba
    0.06
     Wilderness
    0.06
    425
    0.06
    ata
    0.06
    odigo
    0.06
     onCreateViewHolder
    0.06
    Activations Density 0.004%

    No Known Activations