© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55916
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash

    The neuron fires on quoted header‐file include lines (i.e. the “#include "…​.h"” statements).

    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
    _returns
    -0.06
    IDL
    -0.06
     roční
    -0.06
    student
    -0.06
     prune
    -0.06
     aspire
    -0.06
    _gs
    -0.06
     independence
    -0.06
    .sys
    -0.06
    Techn
    -0.06
    POSITIVE LOGITS
     IOException
    0.06
     число
    0.06
     kafka
    0.06
    走
    0.06
    时
    0.06
    SEC
    0.06
     towing
    0.06
    (init
    0.06
    39
    0.06
    _modal
    0.06
    Activations Density 0.004%

    No Known Activations