© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 93715
    Prev
    Next
    INDEX
    Explanations

    constant

    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
    역시
    -0.07
     equipe
    -0.06
    设计器
    -0.06
    eel
    -0.06
    _staff
    -0.06
     frank
    -0.06
    izados
    -0.06
    Witness
    -0.06
     došlo
    -0.06
     서비스
    -0.05
    POSITIVE LOGITS
     Ret
    0.08
     Resets
    0.07
    ucket
    0.07
     ">
    0.07
    ρθρο
    0.07
    (kernel
    0.06
    LESS
    0.06
    _amount
    0.06
     Playlist
    0.06
    _SEGMENT
    0.06
    Activations Density 0.000%

    No Known Activations