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. 84850
    Prev
    Next
    INDEX
    Explanations

    General Text

    np_max-act · gemini-2.0-flash

    The neuron fires on words that appear at the very start of sentences or new paragraphs.

    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
    /video
    -0.07
    rita
    -0.07
    abilia
    -0.07
     Jae
    -0.07
    legal
    -0.07
     třetí
    -0.06
    ritos
    -0.06
     Concepts
    -0.06
     Ki
    -0.06
    dae
    -0.06
    POSITIVE LOGITS
     раствор
    0.07
    present
    0.07
     improbable
    0.06
    ա�
    0.06
    oler
    0.06
    (double
    0.06
    vem
    0.06
    ник
    0.06
     edilmiştir
    0.06
     Fedora
    0.06
    Activations Density 0.086%

    No Known Activations