© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52849
    Prev
    Next
    INDEX
    Explanations

    H

    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_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
    Not in Any Lists

    No Comments

    Negative Logits
     gode
    -0.07
     Possible
    -0.07
     skipping
    -0.07
     confession
    -0.06
     princess
    -0.06
     Totally
    -0.06
     rychle
    -0.06
    储
    -0.06
     apology
    -0.06
    _wheel
    -0.06
    POSITIVE LOGITS
     (%)
    0.07
     _{}
    0.06
     вв
    0.06
    bew
    0.06
    +')
    0.06
    editable
    0.06
    ]];↵
    0.06
     [];
    0.06
     SI
    0.06
    Used
    0.06
    Activations Density 0.005%

    No Known Activations