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. 15-RESID-POST-AA
    6. 123040
    Prev
    Next
    INDEX
    Explanations

    }

    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
     "(\<
    -0.06
     [[]
    -0.06
    .WaitFor
    -0.06
     strconv
    -0.06
    _none
    -0.06
    estli
    -0.06
    олош
    -0.06
    怪
    -0.06
     '../../../../
    -0.06
    ระเบ
    -0.06
    POSITIVE LOGITS
    .tem
    0.08
    Correction
    0.07
    shuffle
    0.07
     ho
    0.06
    ception
    0.06
    М
    0.06
    >+
    0.06
    +
    0.06
     HI
    0.06
     env
    0.06
    Activations Density 0.000%

    No Known Activations