© 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. 73845
    Prev
    Next
    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens that look like floating-point literals (decimal numbers with fractional parts).

    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
    (activity
    -0.06
     �
    -0.06
    distribution
    -0.06
    戶
    -0.06
    ころ
    -0.06
    LayoutParams
    -0.06
    壁
    -0.06
    بول
    -0.05
    овани
    -0.05
    _lit
    -0.05
    POSITIVE LOGITS
     čá
    0.07
     nltk
    0.07
    ively
    0.06
    seeing
    0.06
     cuatro
    0.06
    irectory
    0.06
    =sc
    0.06
     nonatomic
    0.06
     Toolkit
    0.06
     však
    0.06
    Activations Density 0.015%

    No Known Activations