© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12752
    Prev
    Next
    INDEX
    Explanations

    Code component lifecycle events

    np_max-act · gemini-2.0-flash

    The neuron fires on framework lifecycle or initialization method names (e.g. didInsertElement, didReceiveAttrs, initialize, mounted, BufWinEnter).

    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
     vết
    -0.08
     nonatomic
    -0.07
    军
    -0.06
     рек
    -0.06
    Conditions
    -0.06
     when
    -0.06
     购
    -0.06
     '"
    -0.06
     overhe
    -0.06
    akers
    -0.06
    POSITIVE LOGITS
    =>{↵
    0.06
     programa
    0.06
    åde
    0.06
    _Point
    0.06
    :{
↵
    0.06
    -msg
    0.06
    avings
    0.06
     Garten
    0.06
     }↵↵↵
    0.06
     },↵↵↵
    0.06
    Activations Density 0.018%

    No Known Activations