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. 93131
    Prev
    Next
    INDEX
    Explanations

    pa

    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
    üme
    -0.07
    iert
    -0.07
    ektor
    -0.07
    ashboard
    -0.06
     muslim
    -0.06
    ंभ
    -0.06
    иск
    -0.06
     thần
    -0.06
    КТ
    -0.06
     Succ
    -0.06
    POSITIVE LOGITS
     EPA
    0.15
    .capacity
    0.08
     particularly
    0.07
    保
    0.07
    .setSize
    0.07
    шается
    0.07
    iationException
    0.06
     increasingly
    0.06
    ﻴ
    0.06
    ヨ
    0.06
    Activations Density 0.001%

    No Known Activations