© 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. 91210
    Prev
    Next
    INDEX
    Explanations

    natural

    np_max-act · gemini-2.0-flash

    The neuron never activates on any input and thus does not detect any pattern.

    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
    واهد
    -0.06
     هنر
    -0.06
    (Http
    -0.06
     chơi
    -0.06
    /id
    -0.06
    >";
    -0.06
    �
    -0.06
    	box
    -0.05
    .Mod
    -0.05
    /app
    -0.05
    POSITIVE LOGITS
    自然
    0.08
     naturally
    0.07
    seq
    0.07
    >r
    0.07
     Disconnect
    0.06
     provoc
    0.06
     تاريخ
    0.06
    Seq
    0.06
    794
    0.06
    lerdir
    0.06
    Activations Density 0.007%

    No Known Activations