© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 14010
    Prev
    Next
    INDEX
    Explanations

    Organizations and Locations

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens containing decimal points (i.e. floating-point numbers) in the text.

    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
     logistic
    -0.07
    Des
    -0.07
    Mur
    -0.07
    returned
    -0.06
    قم
    -0.06
     pien
    -0.06
    bour
    -0.06
    quat
    -0.06
     divisor
    -0.06
     Erdoğan
    -0.06
    POSITIVE LOGITS
     tartış
    0.07
     jednotlivých
    0.07
    <meta
    0.06
    �
    0.06
    ]}
    0.06
     drove
    0.06
     keypoints
    0.06
     apologize
    0.06
     dó
    0.06
    はず
    0.06
    Activations Density 0.081%

    No Known Activations