© 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. 38126
    Prev
    Next
    INDEX
    Explanations

    apparent

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the phrase “will become apparent,” i.e. that standard patent-boilerplate wording signaling that additional details follow.

    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
     quantity
    -0.07
     go
    -0.07
    Components
    -0.07
     replace
    -0.06
    extension
    -0.06
    iley
    -0.06
    وید
    -0.06
     remarkably
    -0.06
    362
    -0.06
     exchange
    -0.06
    POSITIVE LOGITS
     Orchestra
    0.08
     condos
    0.06
    ess
    0.06
    äl
    0.06
    'l
    0.06
    otal
    0.06
    فة
    0.06
    ]").
    0.06
     Ground
    0.06
    VILLE
    0.06
    Activations Density 0.001%

    No Known Activations