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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 50920
    Prev
    Next
    INDEX
    Explanations

    in/at

    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
     recounted
    -0.07
     Stud
    -0.07
    .singleton
    -0.06
     ώ
    -0.06
    _Register
    -0.06
    racak
    -0.06
     benef
    -0.06
    	Draw
    -0.06
    确定
    -0.06
    solution
    -0.06
    POSITIVE LOGITS
     گذشته
    0.07
    instead
    0.07
    ATED
    0.06
     replacing
    0.06
     FLASH
    0.06
    bis
    0.06
    cold
    0.06
     consolidated
    0.06
     hơi
    0.06
    Invite
    0.06
    Activations Density 0.049%

    No Known Activations