© 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
    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. 89518
    Prev
    Next
    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash

    negative emotional expressions and feelings of frustration or disconnection.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects suggestions that tell the user to “take a step back,” i.e. pauses or reflective break recommendations.

    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
    score
    -0.06
     Số
    -0.06
     profitable
    -0.06
    permalink
    -0.06
     pil
    -0.06
     Mã
    -0.06
    className
    -0.06
     forth
    -0.06
    ัจจ
    -0.06
     lamb
    -0.06
    POSITIVE LOGITS
     DATABASE
    0.06
    album
    0.06
    _SYM
    0.06
     assigns
    0.06
     superClass
    0.06
     warehouse
    0.06
     subjected
    0.06
    Indices
    0.06
     Mansion
    0.06
    _BGR
    0.06
    Activations Density 0.014%

    No Known Activations