© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 53378
    Prev
    Next
    INDEX
    Explanations

    Greetings from different locations

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abbrev
    -0.06
    Behaviour
    -0.06
    eştir
    -0.06
    explicit
    -0.06
    تبة
    -0.06
     avan
    -0.06
     증가
    -0.06
    setChecked
    -0.05
    ']).
    -0.05
     завод
    -0.05
    POSITIVE LOGITS
    \(
    0.07
    더
    0.07
     �
    0.06
     proportions
    0.06
     owns
    0.06
    Md
    0.06
     Remove
    0.06
    #=
    0.06
     hoá
    0.06
    .Drawing
    0.06
    Activations Density 0.022%

    No Known Activations