© 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. 12648
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the pronoun “it” (especially as the subject in “It is …”) in running 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
    inq
    -0.07
    zoom
    -0.07
    operand
    -0.06
    spin
    -0.06
     Genesis
    -0.06
     flashy
    -0.06
    -ip
    -0.06
     цар
    -0.06
    _VLAN
    -0.06
    ril
    -0.06
    POSITIVE LOGITS
     It
    0.10
    We
    0.10
    It
    0.10
     He
    0.10
     She
    0.10
    She
    0.09
     We
    0.09
    They
    0.09
    He
    0.09
     They
    0.09
    Activations Density 0.380%

    No Known Activations