© 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. 89645
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron fires on negative evaluative language—terms expressing adverse impact or bad outcomes (e.g. “negative,” “impact,” “consequences,” “damaging,” etc.).

    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
    _ratings
    -0.07
    막
    -0.07
    	Event
    -0.06
    _bloc
    -0.06
    897
    -0.06
    _act
    -0.06
    yyyyMMdd
    -0.06
    feature
    -0.06
    SpaceItem
    -0.06
    Videos
    -0.06
    POSITIVE LOGITS
     impact
    0.07
     etkisi
    0.06
    	pm
    0.06
     happening
    0.06
     предпоч
    0.06
    'nda
    0.06
    ्थल
    0.06
    esinden
    0.06
     والن
    0.06
    verse
    0.06
    Activations Density 0.047%

    No Known Activations