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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 127582
    Prev
    Next
    INDEX
    Explanations

    Public

    np_max-act · gemini-2.0-flash

    The neuron activates on “License” lines in header comment blocks, i.e. detecting occurrences of the software license declaration.

    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
     Z
    -0.07
     Iv
    -0.07
    ανα
    -0.07
     Esc
    -0.06
     VE
    -0.06
    stricted
    -0.06
     Ign
    -0.06
    (StringUtils
    -0.06
     ALS
    -0.06
     doubling
    -0.06
    POSITIVE LOGITS
    701
    0.08
    ній
    0.06
    Modificar
    0.06
     Укра
    0.06
    _Man
    0.06
     송
    0.06
    ρεια
    0.06
    ılır
    0.06
    αλ
    0.06
     argc
    0.06
    Activations Density 0.001%

    No Known Activations