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. 46272
    Prev
    Next
    INDEX
    Explanations

    of

    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
    τος
    -0.06
    教师
    -0.06
     кли
    -0.06
     चलत
    -0.06
    อากาศ
    -0.06
    Multiplicity
    -0.06
     enactment
    -0.06
    .setLayoutManager
    -0.06
    ुत
    -0.06
    کس
    -0.06
    POSITIVE LOGITS
    heroes
    0.07
     workouts
    0.07
    paint
    0.07
     bowl
    0.06
     RULE
    0.06
    (entry
    0.06
     포
    0.06
     첨부
    0.06
    还
    0.06
     enh
    0.06
    Activations Density 1.216%

    No Known Activations