© 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. 93519
    Prev
    Next
    INDEX
    Explanations

    negative outcomes

    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
     guided
    -0.07
     ус
    -0.06
    stantiate
    -0.06
    '))↵↵↵
    -0.06
    _blocking
    -0.06
    Administrator
    -0.06
    iveness
    -0.06
    なければ
    -0.06
    ());↵↵↵
    -0.06
     boil
    -0.06
    POSITIVE LOGITS
     handicap
    0.08
    ENOMEM
    0.07
    olla
    0.07
     merak
    0.07
     modeling
    0.07
    ("/")
    0.06
    (Locale
    0.06
    (errno
    0.06
    celona
    0.06
     toplumsal
    0.06
    Activations Density 0.085%

    No Known Activations