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. 19-RESID-POST-AA
    6. 83512
    Prev
    Next
    INDEX
    Explanations

    Code syntax

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _utc
    -0.07
     invasive
    -0.06
     breasts
    -0.06
    graph
    -0.06
    Db
    -0.06
     briefly
    -0.06
     measurable
    -0.06
    acz
    -0.06
    HTTPRequest
    -0.06
     supervised
    -0.06
    POSITIVE LOGITS
    ίναι
    0.08
     #__
    0.06
     absolut
    0.06
    _INDEX
    0.06
     liebe
    0.06
     Spiele
    0.06
    окси
    0.06
    centration
    0.06
    Pub
    0.06
     Played
    0.06
    Activations Density 0.040%

    No Known Activations