© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73577
    Prev
    Next
    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on floating-point numeric literals (decimal values like 1.95703125) typically found in comments.

    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
    ading
    -0.07
    ign
    -0.07
     qint
    -0.07
    CEPT
    -0.07
    IGN
    -0.06
    Qty
    -0.06
     Gateway
    -0.06
    012
    -0.06
     Puppet
    -0.06
     القد
    -0.06
    POSITIVE LOGITS
     realism
    0.07
    ulum
    0.06
    (False
    0.06
    ными
    0.06
    <float
    0.06
    %H
    0.06
     Reasons
    0.06
    ịp
    0.06
     Marl
    0.06
     whispers
    0.06
    Activations Density 0.005%

    No Known Activations