© 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. 3-RESID-POST-AA
    11. 121695
    Prev
    Next
    INDEX
    Explanations

    while

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heid
    -0.07
     보호
    -0.07
     RAT
    -0.06
    _printer
    -0.06
     retrospective
    -0.06
     weitere
    -0.06
     erk
    -0.06
     initialized
    -0.06
    orthand
    -0.06
     DVD
    -0.06
    POSITIVE LOGITS
    {-#
    0.09
     Const
    0.07
    ानसभ
    0.06
     Paolo
    0.06
    �
    0.06
     cutoff
    0.06
    플
    0.06
    IMG
    0.06
    จะม
    0.06
    kap
    0.06
    Activations Density 0.002%

    No Known Activations