© 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. 124914
    Prev
    Next
    INDEX
    Explanations

    act

    np_max-act · gemini-2.0-flash

    content related to governmental oversight and ethical concerns in health research.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects occurrences of “redacted” (or “un-redacted”) text indicating material has been censored.

    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
    cred
    -0.07
     Kingston
    -0.06
    γον
    -0.06
    esthetic
    -0.06
     LAB
    -0.06
    $L
    -0.06
    เกาะ
    -0.06
    구글상위
    -0.06
    label
    -0.06
    _PUS
    -0.06
    POSITIVE LOGITS
    .Filters
    0.08
    ุธ
    0.07
     compiled
    0.06
    _supported
    0.06
    >Data
    0.06
     海
    0.06
     ge
    0.06
     Dig
    0.06
     attributes
    0.06
    uent
    0.06
    Activations Density 0.004%

    No Known Activations