© 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. 55993
    Prev
    Next
    INDEX
    Explanations

    Quantifying mentions/geographical locations

    np_max-act · gemini-2.0-flash

    The neuron fires on verbs and nouns tied to protest marches and large demonstrations (e.g. protesting, workers, took to the streets).

    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
    14
    -0.10
    7
    -0.09
    6
    -0.09
    10
    -0.08
    12
    -0.08
    13
    -0.08
    8
    -0.08
    59
    -0.07
    46
    -0.07
     six
    -0.07
    POSITIVE LOGITS
     český
    0.07
     вже
    0.07
     Βροχή
    0.06
    }")
↵
    0.06
     gerekiyor
    0.06
    □□
    0.06
    НО
    0.06
    gatsby
    0.06
    inas
    0.06
    Porno
    0.06
    Activations Density 0.132%

    No Known Activations