Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13275
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric literal tokens (digits and dots) in URLs—i.e. version numbers in CDN/resource links.

    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
    .sleep
    -0.07
     HttpSession
    -0.06
    =event
    -0.06
    (title
    -0.06
     اقتصاد
    -0.06
    aptops
    -0.06
     сер
    -0.06
     Selection
    -0.06
    }↵↵↵↵
    -0.06
     tamaño
    -0.06
    POSITIVE LOGITS
     Newly
    0.07
    dbname
    0.06
    apollo
    0.06
     brace
    0.06
    ScreenState
    0.06
    plete
    0.06
    athed
    0.06
    _clock
    0.06
    chaft
    0.06
    _UPLOAD
    0.06
    Activations Density 0.006%

    No Known Activations