Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 7-RESID-POST-AA
    6. 93220
    Prev
    Next
    INDEX
    Explanations

    hypertension drugs

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancybox
    -0.07
     BOOST
    -0.06
    rende
    -0.06
     Mobility
    -0.06
     sıra
    -0.06
     мати
    -0.06
     diplomats
    -0.06
    �ت
    -0.06
                                                                        
    -0.06
     стати
    -0.06
    POSITIVE LOGITS
     серд
    0.08
    Aud
    0.07
    rax
    0.07
     SSL
    0.07
    /Peak
    0.06
     mango
    0.06
     vex
    0.06
     pcm
    0.06
     Complete
    0.06
     кар
    0.06
    Activations Density 0.005%

    No Known Activations