© 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. 23-RESID-POST-AA
    6. 7914
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    et
    -0.07
    ěti
    -0.06
    ewart
    -0.06
     overcoming
    -0.06
    aked
    -0.06
     mitigate
    -0.06
     voting
    -0.06
    .et
    -0.06
     هنگ
    -0.06
     arma
    -0.06
    POSITIVE LOGITS
     this
    0.17
     THIS
    0.12
     This
    0.12
    This
    0.11
    	this
    0.10
    this
    0.10
     here
    0.09
    -this
    0.09
    .This
    0.08
     these
    0.08
    Activations Density 0.389%

    No Known Activations