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. 7-RESID-POST-AA
    6. 93282
    Prev
    Next
    INDEX
    Explanations

    Bro

    np_max-act · gemini-2.0-flash

    Bro

    np_max-act · gemini-2.5-flashTriggered by @aardvarkkr

    words that begin with the letter sequence "Bro".

    oai_token-act-pair · gemini-2.5-flashTriggered by @aardvarkkr
    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
     стало
    -0.07
    .'&
    -0.07
    .scala
    -0.07
    داری
    -0.07
     ні
    -0.06
    σο
    -0.06
     ');
    ↵
    -0.06
    /API
    -0.06
     терап
    -0.06
    .hxx
    -0.06
    POSITIVE LOGITS
     의해
    0.06
    igt
    0.06
     partner
    0.06
    نسية
    0.06
     umb
    0.06
    Brun
    0.06
     junction
    0.06
    yleft
    0.06
     Muss
    0.06
    (fr
    0.06
    Activations Density 0.359%

    No Known Activations