© 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. 11-RESID-POST-AA
    11. 74999
    Prev
    Next
    INDEX
    Explanations

    reinforced

    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
    -datepicker
    -0.08
     PHY
    -0.07
     Expires
    -0.07
     sit
    -0.07
     δυ
    -0.07
     mbox
    -0.06
    (xx
    -0.06
     Array
    -0.06
    398
    -0.06
    haps
    -0.06
    POSITIVE LOGITS
     reinforce
    0.14
     reinforced
    0.13
     reinforcing
    0.12
     reinforces
    0.10
     reinforcements
    0.10
     reinforcement
    0.08
    ein
    0.08
     Rein
    0.08
    uin
    0.08
     Wing
    0.08
    Activations Density 0.006%

    No Known Activations