© 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. 41340
    Prev
    Next
    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash

    The neuron fires on “Read more” link texts—i.e. prompts or anchor text inviting the reader to “Read more.”

    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
    еред
    -0.06
    (rot
    -0.06
    xima
    -0.06
     opt
    -0.06
    Transmission
    -0.06
    906
    -0.06
    substring
    -0.06
    .arr
    -0.06
     replace
    -0.06
     Ultr
    -0.06
    POSITIVE LOGITS
     more
    0.08
     essence
    0.07
     PURPOSE
    0.07
    :message
    0.07
     strom
    0.07
    »↵
    0.07
    ाड
    0.07
    haar
    0.06
     parked
    0.06
     tee
    0.06
    Activations Density 0.006%

    No Known Activations