Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96033
    Prev
    Next
    INDEX
    Explanations

    entities and specific keywords related to food items and culinary terms

    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
     INTERRUPTION
    -0.10
    redient
    -0.08
    reet
    -0.08
    edla
    -0.07
    resa
    -0.07
     PLUGIN
    -0.07
    icode
    -0.07
    aign
    -0.07
    ISIBLE
    -0.07
    styleType
    -0.07
    POSITIVE LOGITS
     cen
    0.07
     mad
    0.06
     bouncing
    0.06
     MO
    0.06
     g
    0.05
     Lambert
    0.05
     unc
    0.05
     f
    0.05
     bare
    0.05
     conglomer
    0.05
    Activations Density 0.036%

    No Known Activations