© 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. 125772
    Prev
    Next
    INDEX
    Explanations

    ingredients and quantities related to food recipes

    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
    esser
    -0.07
    :CGRect
    -0.07
    dess
    -0.06
    Å¡ku
    -0.06
     Mueller
    -0.06
    glob
    -0.06
    annis
    -0.06
    리ìĬ¤
    -0.06
    421
    -0.06
    extensions
    -0.06
    POSITIVE LOGITS
     inside
    0.08
     interiors
    0.07
    Inside
    0.07
    inside
    0.07
     payloads
    0.07
     interior
    0.07
    åĨħéĥ¨
    0.07
     filling
    0.06
     stuffing
    0.06
     enc
    0.06
    Activations Density 0.040%

    No Known Activations