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. 130409
    Prev
    Next
    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash

    This neuron responds to placeholder name tokens (e.g. “NAME_1,” “NAME_2,” etc.).

    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
    	system
    -0.07
     Dah
    -0.07
     Distributed
    -0.07
    Angel
    -0.07
    �
    -0.06
    =fopen
    -0.06
     kavram
    -0.06
    被
    -0.06
    .Console
    -0.06
    tier
    -0.06
    POSITIVE LOGITS
    днання
    0.07
    (Activity
    0.07
     друж
    0.07
     bulunmaktadır
    0.06
     disclosing
    0.06
     Reasons
    0.06
    gement
    0.06
     Απο
    0.06
    startswith
    0.06
     Converted
    0.06
    Activations Density 0.074%

    No Known Activations