© 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. 128591
    Prev
    Next
    INDEX
    Explanations

    %

    np_max-act · gemini-2.0-flash

    This neuron does not activate on any text and thus does not detect any patterns (i.e., it is effectively “dead”).

    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
     mover
    -0.07
     Daw
    -0.06
     vyjád
    -0.06
    47
    -0.06
     lign
    -0.06
    načení
    -0.06
     bul
    -0.06
    атків
    -0.06
    [line
    -0.06
     Dong
    -0.06
    POSITIVE LOGITS
    %
    0.13
     percent
    0.11
    )%
    0.11
    ी
    0.10
    ]%
    0.09
     %
    0.09
     νεφοκ
    0.08
     percentage
    0.08
    isc
    0.08
    %)
    0.08
    Activations Density 0.069%

    No Known Activations