© 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. 57929
    Prev
    Next
    INDEX
    Explanations

    vibrational

    np_max-act · gemini-2.0-flash

    The neuron activates on subwords related to vibrational analysis (e.g. “vibrational,” “anharmonic,” “harmonic”), effectively detecting mentions of vibrational spectra or frequencies.

    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
     Sharks
    -0.07
     Aberdeen
    -0.06
    όδ
    -0.06
     hood
    -0.06
     Il
    -0.06
     idi
    -0.06
     potrav
    -0.06
    vou
    -0.06
     ominous
    -0.06
     dostat
    -0.06
    POSITIVE LOGITS
     automát
    0.06
     academics
    0.06
     envi
    0.06
     Serv
    0.06
    ρον
    0.06
    iễn
    0.06
     grad
    0.06
    linear
    0.06
     cooperative
    0.06
    env
    0.06
    Activations Density 0.005%

    No Known Activations