© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109403
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on passive‐voice phrases that describe the granting or assignment of rights, privileges, or concessions (e.g. “concession awarded to,” “assigned to,” “privileges of”).

    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
     könnte
    -0.07
    URLException
    -0.07
     premium
    -0.07
    shade
    -0.07
    264
    -0.07
    rms
    -0.07
    číta
    -0.06
    daily
    -0.06
    Wie
    -0.06
    แส
    -0.06
    POSITIVE LOGITS
    belongsTo
    0.07
    len
    0.06
     wah
    0.06
    dat
    0.06
    (newUser
    0.06
     advertis
    0.06
    ↵↵
    0.06
     quale
    0.06
     SNP
    0.06
     佐
    0.06
    Activations Density 0.043%

    No Known Activations