Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 130523
    Prev
    Next
    INDEX
    Explanations

    Increasing or getting worse

    np_max-act · gemini-2.0-flash

    The neuron detects words and phrases that describe the growing intensity or escalation of sounds or sensations (e.g. louder, more, intense, continue).

    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
     figsize
    -0.07
    reatment
    -0.07
     müdür
    -0.07
    .setHorizontalAlignment
    -0.07
     мед
    -0.06
     smiled
    -0.06
     Müdür
    -0.06
    .yang
    -0.06
     punch
    -0.06
    스토
    -0.06
    POSITIVE LOGITS
    interested
    0.06
     ogl
    0.06
     Quản
    0.06
     prog
    0.06
    vrir
    0.06
    prob
    0.06
    จะได
    0.06
     ğ
    0.06
    way
    0.06
     proving
    0.06
    Activations Density 0.022%

    No Known Activations