© 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. 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. 43275
    Prev
    Next
    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the token “string” (e.g. in type or header names).

    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
     va
    -0.06
     Healthcare
    -0.06
     fever
    -0.06
     Fever
    -0.06
     EC
    -0.06
    (rec
    -0.06
     Voc
    -0.06
    (rv
    -0.06
     worked
    -0.06
     occurred
    -0.06
    POSITIVE LOGITS
    String
    0.11
     string
    0.11
    string
    0.11
    _string
    0.10
    송
    0.09
     String
    0.09
    ToString
    0.09
    -string
    0.09
    STRING
    0.09
    queryString
    0.09
    Activations Density 0.071%

    No Known Activations