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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 54062
    Prev
    Next
    INDEX
    Explanations

    on

    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
    )c
    -0.07
     kw
    -0.06
     informed
    -0.06
     boxes
    -0.06
    Pres
    -0.06
     DESC
    -0.06
    ASHBOARD
    -0.06
     SEN
    -0.06
    ?a
    -0.06
     Akt
    -0.06
    POSITIVE LOGITS
    Vue
    0.06
     音
    0.06
    	On
    0.06
    _you
    0.06
     září
    0.06
     قانون
    0.06
     chụp
    0.05
     económ
    0.05
    解
    0.05
    _ul
    0.05
    Activations Density 0.008%

    No Known Activations