© 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. 78026
    Prev
    Next
    INDEX
    Explanations

    facial conditions

    np_max-act · gemini-2.0-flash

    words related to facial conditions and medical diagnoses involving the face.

    oai_token-act-pair · gpt-4o-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
     němu
    -0.07
     jente
    -0.07
    hend
    -0.07
     weiber
    -0.07
    (('
    -0.06
     '".$_
    -0.06
    ------+------+
    -0.06
     obliged
    -0.06
    ='_
    -0.06
     rumpe
    -0.06
    POSITIVE LOGITS
     facial
    0.10
     Facial
    0.09
    odial
    0.08
    قد
    0.07
    stitial
    0.07
     casual
    0.07
    fac
    0.07
    ilia
    0.07
     Gl
    0.07
     Eastern
    0.07
    Activations Density 0.002%

    No Known Activations