© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47774
    Prev
    Next
    INDEX
    Explanations

    transcript excerpts

    np_max-act · gemini-2.0-flash

    words and phrases related to relationship inquiries and emotional connections.

    oai_token-act-pair · gpt-4o-mini
    Triggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    osphate
    -0.07
    instances
    -0.06
     �
    -0.06
    appen
    -0.06
    _DAT
    -0.06
    juan
    -0.06
     instances
    -0.06
    рами
    -0.06
    ุมภาพ
    -0.06
    .getSelected
    -0.06
    POSITIVE LOGITS
    (cb
    0.06
     retr
    0.06
    (Content
    0.06
    <Tuple
    0.06
    ١
    0.06
    }↵
    0.06
     towering
    0.06
    �
    0.06
    representation
    0.06
     setLoading
    0.06
    Activations Density 0.025%

    No Known Activations