© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 5917
    Prev
    Next
    INDEX
    Explanations

    Actions and occurrences

    np_max-act · gemini-2.0-flash

    The neuron is picking up occurrences of the auxiliary verb “do” (e.g. “does,” “do,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    },{
    -0.07
    -time
    -0.06
    DTO
    -0.06
    etě
    -0.06
    �ng
    -0.06
    퇴
    -0.06
    Scan
    -0.05
     Bentley
    -0.05
    -bin
    -0.05
     použít
    -0.05
    POSITIVE LOGITS
    �
    0.07
    __(*
    0.07
     Eq
    0.07
     shy
    0.06
     dov
    0.06
     教
    0.06
     mant
    0.06
    _download
    0.06
    rgb
    0.06
    udiant
    0.06
    Activations Density 0.043%

    No Known Activations