© 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. 15-RESID-POST-AA
    6. 124765
    Prev
    Next
    INDEX
    Explanations

    translation

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _using
    -0.07
    _PULL
    -0.07
    }px
    -0.07
    -IS
    -0.07
     Democrat
    -0.06
     Pou
    -0.06
    aris
    -0.06
    ILog
    -0.06
    losure
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Dě
    0.07
    ování
    0.07
     adv
    0.07
     začí
    0.07
    ilmiştir
    0.06
     unic
    0.06
     boğ
    0.06
     ニ
    0.06
     dài
    0.06
    =Integer
    0.06
    Activations Density 0.000%

    No Known Activations