© 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. 56527
    Prev
    Next
    INDEX
    Explanations

    Academic/Professional text

    np_max-act · gemini-2.0-flash

    The neuron fires on terminology related to CNNs’ image‐processing/computer‐vision tasks (e.g. “image,” “recognition,” “spatial,” “vision”).

    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
     unicorn
    -0.07
    ิโน
    -0.06
     +#+
    -0.06
     dobr
    -0.06
     ruk
    -0.06
     сотруд
    -0.06
    apphire
    -0.06
     Axe
    -0.06
     如果
    -0.06
    如果
    -0.06
    POSITIVE LOGITS
    atomic
    0.08
     Tom
    0.07
    itone
    0.06
    dimensions
    0.06
    .global
    0.06
    	curl
    0.06
    -gradient
    0.06
        ↵
    0.06
     입력
    0.06
     enzymes
    0.06
    Activations Density 0.142%

    No Known Activations