© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73756
    Prev
    Next
    INDEX
    Explanations

    sprite

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric tokens—especially floating‐point numbers (e.g. “3.259765625,” “0.435791015625,” etc.) in the serialized metadata.

    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
     prosince
    -0.07
    efa
    -0.06
    #c
    -0.06
    .failure
    -0.06
     ANAL
    -0.06
     června
    -0.06
    anal
    -0.06
    StartupScript
    -0.06
     opět
    -0.06
     internet
    -0.06
    POSITIVE LOGITS
     شيء
    0.08
     tweets
    0.07
     dwarf
    0.06
     gathered
    0.06
    -bo
    0.06
     Under
    0.06
     supra
    0.06
    イズ
    0.06
    _friend
    0.06
     small
    0.06
    Activations Density 0.001%

    No Known Activations