© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110265
    Prev
    Next
    INDEX
    Explanations

    officer

    np_max-act · gemini-2.0-flash

    This neuron lights up on technical terms describing database models or data‐structure types (e.g., “relational,” “non-relational,” “semi-structured,” “graph,” “key-value,” “documents”).

    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
    verbs
    -0.07
    FormData
    -0.06
    uintptr
    -0.06
     yemek
    -0.06
     poste
    -0.06
     ده
    -0.06
    mdir
    -0.06
    าะห
    -0.06
     суд
    -0.06
     ngOnInit
    -0.06
    POSITIVE LOGITS
    182
    0.06
    Henry
    0.06
     spaced
    0.06
    Notice
    0.06
     PSP
    0.06
     Electric
    0.05
     WON
    0.05
     gost
    0.05
     maxx
    0.05
     Seattle
    0.05
    Activations Density 0.066%

    No Known Activations