© 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 EvalsExportsinterp-engineNEWAPI 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. 58572
    Prev
    Next
    INDEX
    Explanations

    camera lenses

    np_max-act · gemini-2.0-flash

    This neuron detects numeric camera‐lens specifications—particularly focal length values (e.g. “25 mm,” “85 mm,” “90 mm f/2.8”) and related measurement tokens.

    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
    _byte
    -0.06
     ocas
    -0.06
     consciousness
    -0.06
    비아
    -0.06
    �
    -0.06
     Vegas
    -0.06
     sadd
    -0.06
     sean
    -0.06
    ensors
    -0.06
     Scient
    -0.05
    POSITIVE LOGITS
    整个
    0.07
    ={↵
    0.07
     projected
    0.07
    dk
    0.07
     mandatory
    0.07
    buster
    0.06
     Healthy
    0.06
    .Controllers
    0.06
    Arena
    0.06
    __)↵
    0.06
    Activations Density 0.008%

    No Known Activations