© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 60469
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Discount
    -0.07
     pickerView
    -0.07
     갤
    -0.06
     editText
    -0.06
    richText
    -0.06
    (anchor
    -0.06
     الطبي
    -0.06
     Paran
    -0.06
     positional
    -0.06
    +");↵
    -0.06
    POSITIVE LOGITS
    Microsoft
    0.06
    ios
    0.06
     universally
    0.06
    )==
    0.06
    BED
    0.06
    ')==
    0.06
     đứng
    0.05
    	move
    0.05
     залеж
    0.05
    college
    0.05
    Activations Density 0.038%

    No Known Activations