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. 19-RESID-POST-AA
    6. 57272
    Prev
    Next
    INDEX
    Explanations

    negative concepts

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     waiver
    -0.07
    	version
    -0.07
    (attributes
    -0.07
     termed
    -0.07
     whose
    -0.06
     premiered
    -0.06
     directive
    -0.06
     reservation
    -0.06
     Adds
    -0.06
     दव
    -0.06
    POSITIVE LOGITS
     ugly
    0.09
    ♀♀♀♀
    0.07
    .TYPE
    0.07
    _Max
    0.07
    mentation
    0.07
     glColor
    0.06
     ऊ
    0.06
     استر
    0.06
     �
    0.06
     MPU
    0.06
    Activations Density 0.004%

    No Known Activations