© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30036
    Prev
    Next
    INDEX
    Explanations

    groupings or patterns

    np_max-act · gemini-2.0-flash

    The neuron responds to words that denote collections or groupings (e.g. “cluster,” “group”).

    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
     ghost
    -0.06
     buổi
    -0.06
     века
    -0.06
    _FD
    -0.06
    _mgmt
    -0.06
     aft
    -0.06
    (*(
    -0.06
     Además
    -0.06
     Leban
    -0.05
    	 ↵
    -0.05
    POSITIVE LOGITS
     seç
    0.06
     Exped
    0.06
    LETE
    0.06
    _radi
    0.06
    。而
    0.06
    fidf
    0.06
    .microsoft
    0.06
     trä
    0.06
     �
    0.06
    245
    0.06
    Activations Density 0.083%

    No Known Activations