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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-RESID-POST-AA
    6. 104213
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     シ
    -0.07
    配
    -0.07
     принцип
    -0.07
     rng
    -0.06
     sollte
    -0.06
     отрим
    -0.06
    throat
    -0.06
     changed
    -0.06
    乃
    -0.06
    -track
    -0.06
    POSITIVE LOGITS
    _FAILURE
    0.06
    (KP
    0.06
    ��取
    0.06
    üyük
    0.06
     NSURL
    0.06
    ERNEL
    0.06
    _REC
    0.06
    -angle
    0.06
     Hernandez
    0.06
    .background
    0.06
    Activations Density 0.011%

    No Known Activations