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

    Neuronpedia

    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. 129897
    Prev
    Next
    INDEX
    Explanations

    pharmaceuticals

    np_max-act · gemini-2.0-flash

    connections between solid dispersion formulations and drug dissolution rates.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects technical terms related to pharmaceutical solid‐state formulation processes and properties.

    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
     honoured
    -0.06
     mechanics
    -0.06
     bleeding
    -0.06
    "Oh
    -0.06
    Anonymous
    -0.06
    _df
    -0.06
     Deadline
    -0.06
    INCLUDED
    -0.06
     pm
    -0.06
    Bed
    -0.06
    POSITIVE LOGITS
    ství
    0.07
     六
    0.07
     свет
    0.07
     budouc
    0.07
    рид
    0.07
    eview
    0.06
    キング
    0.06
    .handleSubmit
    0.06
    _qual
    0.06
     bakış
    0.06
    Activations Density 0.025%

    No Known Activations