© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92169
    Prev
    Next
    INDEX
    Explanations

    programming loops and checks

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on segments of foreign‐language (here Portuguese) text, especially accentuated or non-English tokens.

    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
    ражд
    -0.07
    ดำ
    -0.07
    _Framework
    -0.07
    ντ
    -0.07
     cuenta
    -0.07
     页面
    -0.07
    .use
    -0.07
    ุค
    -0.06
    ّه
    -0.06
    _Internal
    -0.06
    POSITIVE LOGITS
    FFFF
    0.07
    	NULL
    0.06
    _help
    0.06
     JIT
    0.06
    .hadoop
    0.06
    .fixed
    0.06
     suites
    0.06
     Jess
    0.06
    ovah
    0.06
    xAF
    0.05
    Activations Density 0.052%

    No Known Activations