© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38783
    Prev
    Next
    INDEX
    Explanations

    video motion encoding

    np_max-act · gemini-2.0-flash

    The neuron activates on technical terms naming video coding methods and prediction modes (e.g. spatial, temporal, intra-, inter-).

    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
    sss
    -0.06
    JUST
    -0.06
     CPU
    -0.06
    kate
    -0.06
     reef
    -0.06
    SHOT
    -0.06
    Pow
    -0.06
    edar
    -0.06
     lun
    -0.06
     <--
    -0.06
    POSITIVE LOGITS
    พระ
    0.07
     encompass
    0.06
     район
    0.06
    گاه
    0.06
    (piece
    0.06
    甚至
    0.06
     dej
    0.06
    コメント
    0.06
     mother
    0.06
    .ViewHolder
    0.06
    Activations Density 0.001%

    No Known Activations