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. 3-RESID-POST-AA
    6. 122082
    Prev
    Next
    INDEX
    Explanations

    ase

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _MPI
    -0.07
     Rupert
    -0.06
    yg
    -0.06
     قابلیت
    -0.06
    敢
    -0.06
    狂
    -0.06
     XYZ
    -0.06
     vydání
    -0.06
    छ
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     postgres
    0.19
     jazz
    0.10
    postgres
    0.07
    .StartsWith
    0.07
    评
    0.07
     talking
    0.06
    ?family
    0.06
     ambiance
    0.06
                
    ↵
    0.06
     chees
    0.06
    Activations Density 0.003%

    No Known Activations