© 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. 7-RESID-POST-AA
    11. 96268
    Prev
    Next
    INDEX
    Explanations

    Collectors

    np_max-act · gemini-2.0-flash

    that it never activates — it doesn't detect any token patterns (effectively an inactive neuron).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alk
    -0.08
    ř
    -0.07
     openness
    -0.07
    赵
    -0.07
     upwards
    -0.06
     Bryce
    -0.06
     nationwide
    -0.06
     lithium
    -0.06
     immigration
    -0.06
    Rank
    -0.06
    POSITIVE LOGITS
    (Collectors
    0.15
    .Collectors
    0.13
    Schedulers
    0.08
    mutation
    0.07
     composers
    0.07
    .Areas
    0.06
    단체
    0.06
    จะเป
    0.06
    .GetKey
    0.06
     مشاهدة
    0.06
    Activations Density 0.000%

    No Known Activations