Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 123780
    Prev
    Next
    INDEX
    Explanations

    a

    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
    <count
    -0.06
    �
    -0.06
    lowest
    -0.06
     tactic
    -0.06
     худ
    -0.06
    191
    -0.06
    ật
    -0.06
    Ve
    -0.06
    博
    -0.06
    萬
    -0.06
    POSITIVE LOGITS
     componentDid
    0.07
     narrowly
    0.07
     者
    0.07
     }]
    0.07
    ;width
    0.07
    っぱい
    0.07
     bone
    0.06
    ('$
    0.06
     порядку
    0.06
     secara
    0.06
    Activations Density 0.243%

    No Known Activations