© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 93940
    Prev
    Next
    INDEX
    Explanations

    pret

    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
     Champion
    -0.07
    oire
    -0.07
     utils
    -0.06
    _branch
    -0.06
    Trace
    -0.06
    ��
    -0.06
    -lite
    -0.06
    �y
    -0.06
    مند
    -0.06
    lox
    -0.06
    POSITIVE LOGITS
     pret
    0.26
     Pret
    0.14
    pret
    0.09
     Bannon
    0.07
     тих
    0.07
    怒
    0.06
     Aut
    0.06
     AUT
    0.06
     Changing
    0.06
    sk
    0.06
    Activations Density 0.001%

    No Known Activations