© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91142
    Prev
    Next
    INDEX
    Explanations

    ice

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the substring “ice,” effectively detecting the token “ice.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ferdinand
    -0.07
     Freund
    -0.07
    164
    -0.07
     comprehend
    -0.07
     srov
    -0.07
     Tal
    -0.07
     Fon
    -0.06
     transmitted
    -0.06
    344
    -0.06
    ενο
    -0.06
    POSITIVE LOGITS
     ice
    0.18
     Ice
    0.16
    Ice
    0.16
     ICE
    0.11
    ices
    0.10
    ice
    0.09
     icy
    0.09
    IC
    0.08
    ici
    0.08
     iceberg
    0.08
    Activations Density 0.007%

    No Known Activations