© 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 (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 40792
    Prev
    Next
    INDEX
    Explanations

    oxidation

    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
    ス
    -0.07
     نسخ
    -0.07
    fest
    -0.07
     dispers
    -0.06
     beforehand
    -0.06
     bas
    -0.06
     WM
    -0.06
    (TM
    -0.06
     meme
    -0.06
     fra
    -0.06
    POSITIVE LOGITS
    .asm
    0.06
     _$
    0.06
    _$_
    0.06
    ationally
    0.06
    .Short
    0.06
    .');↵↵
    0.06
    Output
    0.06
    riott
    0.06
    hya
    0.06
     Estonia
    0.06
    Activations Density 0.203%

    No Known Activations