© 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. 8997
    Prev
    Next
    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash

    The neuron responds to multi‐letter uppercase sequences and initialisms (e.g. acronyms or romanized proper‐name fragments).

    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
    -new
    -0.07
    /high
    -0.06
    Clr
    -0.06
    20
    -0.06
     지난
    -0.06
    hythm
    -0.06
    $page
    -0.06
     concentr
    -0.06
     Blond
    -0.06
     Hole
    -0.06
    POSITIVE LOGITS
     RJ
    0.11
     RS
    0.10
     RM
    0.10
     RP
    0.09
    RCT
    0.09
     RW
    0.09
     RK
    0.09
     RMS
    0.09
     Ramos
    0.09
     RL
    0.09
    Activations Density 0.738%

    No Known Activations