© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55472
    Prev
    Next
    INDEX
    Explanations

    probability

    np_max-act · gemini-2.0-flash

    This neuron fires on probability-related expressions, in particular on “prob” and the numeric probability values in the text.

    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
     shading
    -0.08
    .part
    -0.06
     outputs
    -0.06
    áz
    -0.06
    ">#
    -0.06
     hypertension
    -0.06
     kli
    -0.05
    振
    -0.05
     акту
    -0.05
     Figures
    -0.05
    POSITIVE LOGITS
     Deus
    0.07
    (mb
    0.07
    ¬
    0.07
    anoi
    0.07
    getInstance
    0.07
     يونيو
    0.07
    ounc
    0.07
    ucken
    0.07
    izzer
    0.06
     Tes
    0.06
    Activations Density 0.002%

    No Known Activations