© 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. 89632
    Prev
    Next
    INDEX
    Explanations

    limb

    np_max-act · gemini-2.0-flash

    This neuron is triggered by specialized technical or scientific jargon terms (e.g. “electron,” “depth,” “graph,” “kidney,” “engine”) in the text.

    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
     game
    -0.07
    wrap
    -0.07
     absorbing
    -0.07
    宫
    -0.06
    apture
    -0.06
    .ibm
    -0.06
     films
    -0.06
    .run
    -0.06
    scroll
    -0.06
    Profiles
    -0.06
    POSITIVE LOGITS
    \Php
    0.07
    ($_
    0.07
     gboolean
    0.07
     ↘
    0.07
     esac
    0.06
     Demp
    0.06
    ské
    0.06
    %H
    0.06
    �
    0.06
    (!_
    0.06
    Activations Density 0.190%

    No Known Activations