© 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. 37995
    Prev
    Next
    INDEX
    Explanations

    Benzene and related chemicals

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of basic aromatic hydrocarbon feedstocks (e.g. benzene, toluene, xylene) used as raw materials.

    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
     hitters
    -0.07
    	glBind
    -0.06
    utoff
    -0.06
    "-
    -0.06
     IT
    -0.06
     incarnation
    -0.06
    Pont
    -0.06
    itors
    -0.06
    .digital
    -0.06
    'It
    -0.06
    POSITIVE LOGITS
    ene
    0.09
    .MiddleCenter
    0.08
    هم
    0.08
     complex
    0.07
    alex
    0.07
    �
    0.07
    け
    0.07
    埋
    0.07
     dış
    0.07
     accessibility
    0.07
    Activations Density 0.008%

    No Known Activations