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. 19-RESID-POST-AA
    6. 111858
    Prev
    Next
    INDEX
    Explanations

    plants and gardening

    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
     prisons
    -0.06
    ningen
    -0.06
    联合
    -0.06
     businessman
    -0.06
    แนะนำ
    -0.06
    Пос
    -0.06
    _CHARACTER
    -0.06
     दर
    -0.06
    jections
    -0.06
     Terrorism
    -0.06
    POSITIVE LOGITS
     oppressive
    0.07
     ns
    0.07
     empath
    0.06
     arousal
    0.06
     opener
    0.06
     desp
    0.06
     chai
    0.06
     apparatus
    0.06
    'article
    0.06
     movable
    0.06
    Activations Density 0.028%

    No Known Activations