© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 110139
    Prev
    Next
    INDEX
    Explanations

    simply

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dolore
    -0.06
    iOS
    -0.06
     vẽ
    -0.06
    _Array
    -0.06
     dobré
    -0.06
     Este
    -0.06
    Ocean
    -0.06
     predominantly
    -0.06
     SOURCE
    -0.06
    _Module
    -0.06
    POSITIVE LOGITS
    (abs
    0.07
    Still
    0.07
     노출
    0.06
    ضا
    0.06
    став
    0.06
    }elseif
    0.06
    偷
    0.06
     decrypt
    0.06
    still
    0.06
    μως
    0.06
    Activations Density 0.040%

    No Known Activations