© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89100
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on floating‐point numeric literals (decimal numbers) in the code.

    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
    омі
    -0.06
    �
    -0.06
     consort
    -0.06
    ‌ی
    -0.06
     separator
    -0.06
     thủy
    -0.06
     Separator
    -0.06
    _wheel
    -0.06
    emale
    -0.06
     Listener
    -0.06
    POSITIVE LOGITS
    RID
    0.08
     TECH
    0.07
     Lie
    0.06
     injuring
    0.06
    _VERBOSE
    0.06
    τηγορία
    0.06
     Auto
    0.06
     CLOSED
    0.06
     INCIDENT
    0.06
            				
    0.06
    Activations Density 0.008%

    No Known Activations