Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 46129
    Prev
    Next
    INDEX
    Explanations

    like

    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
     beyond
    -0.07
    츠
    -0.07
    �果
    -0.06
     Smooth
    -0.06
    lied
    -0.06
    σα
    -0.06
    иш
    -0.06
    зано
    -0.06
     killers
    -0.06
     responsable
    -0.06
    POSITIVE LOGITS
     px
    0.07
     IND
    0.07
     Cart
    0.06
     resembles
    0.06
     (($
    0.06
    -Ch
    0.06
     sunscreen
    0.06
    -Re
    0.06
     المن
    0.06
     showToast
    0.06
    Activations Density 0.027%

    No Known Activations