© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 10984
    Prev
    Next
    INDEX
    Explanations

    Professorships and people

    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
    Field
    -0.06
    8
    -0.06
    交易
    -0.06
    mute
    -0.06
    way
    -0.06
    icted
    -0.06
     females
    -0.06
    san
    -0.06
     plur
    -0.06
    Char
    -0.05
    POSITIVE LOGITS
    (IOException
    0.09
    >(),↵
    0.08
     Predator
    0.08
    ++]=
    0.08
    žití
    0.07
    	AT
    0.07
     ~~
    0.07
    ////////////////////////////////////////////////////////////////////////////////
    0.07
    	mkdir
    0.07
    award
    0.07
    Activations Density 0.018%

    No Known Activations