© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 92156
    Prev
    Next
    INDEX
    Explanations

    io

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the substring “istio” (i.e. mentions of the Istio name) in configuration 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
    Police
    -0.08
     dafür
    -0.07
     облі
    -0.07
    Telefone
    -0.06
    .Are
    -0.06
    $post
    -0.06
    Exam
    -0.06
     Overnight
    -0.06
     dime
    -0.06
    Exc
    -0.06
    POSITIVE LOGITS
     означа
    0.07
     польз
    0.07
    DH
    0.07
    روع
    0.06
     βιβ
    0.06
     signify
    0.06
     из
    0.06
     DL
    0.06
    rup
    0.06
    .ctrl
    0.06
    Activations Density 0.002%

    No Known Activations