© 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. 56750
    Prev
    Next
    INDEX
    Explanations

    selling/giving away unwanted items

    np_max-act · gemini-2.0-flash

    The neuron detects phrases and words that indicate an item is being offered for sale (e.g. “for sale,” “selling,” “I no longer need,” “contact me”).

    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
     nuestra
    -0.07
     機
    -0.06
    -es
    -0.06
     fert
    -0.06
    Earth
    -0.06
     fists
    -0.06
     براي
    -0.06
     那
    -0.06
     byli
    -0.06
    835
    -0.06
    POSITIVE LOGITS
    Sortable
    0.07
    .modelo
    0.07
    ENAME
    0.07
    _FALSE
    0.06
     TRY
    0.06
     dolay
    0.06
    .GetCurrentMethod
    0.06
    .program
    0.06
    .units
    0.06
     guitarist
    0.06
    Activations Density 0.022%

    No Known Activations