© 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. 3-RESID-POST-AA
    6. 123018
    Prev
    Next
    INDEX
    Explanations

    cell culture

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JSONObject
    -0.07
    发展
    -0.06
     manžel
    -0.06
    İTESİ
    -0.06
     potatoes
    -0.06
    ez
    -0.06
    <Double
    -0.06
    	max
    -0.06
     manufactured
    -0.06
     mother
    -0.06
    POSITIVE LOGITS
    _locator
    0.07
    adresse
    0.07
     ấn
    0.07
    :black
    0.06
    ergy
    0.06
    _resolver
    0.06
    .ReadUInt
    0.06
    бут
    0.06
    olocation
    0.06
     rij
    0.06
    Activations Density 0.004%

    No Known Activations