© 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. 121744
    Prev
    Next
    INDEX
    Explanations

    hard

    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
     espionage
    -0.07
    Qi
    -0.07
     cresc
    -0.07
     {:
    -0.07
     зов
    -0.07
     Helvetica
    -0.06
     aos
    -0.06
    _<
    -0.06
    َع
    -0.06
    .nextElement
    -0.06
    POSITIVE LOGITS
     hard
    0.13
     harder
    0.08
     hardness
    0.07
     getTotal
    0.07
     Utilities
    0.06
    ै.↵
    0.06
     crc
    0.06
     Мед
    0.06
    .Card
    0.06
     workshop
    0.06
    Activations Density 0.012%

    No Known Activations