© 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. 126132
    Prev
    Next
    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the verb “used” (especially in comments or documentation).

    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
    _rotate
    -0.07
    pants
    -0.06
    かの
    -0.06
    移到
    -0.06
    restrict
    -0.06
    idia
    -0.06
     Bl
    -0.06
    	dc
    -0.06
     manufacturers
    -0.06
    iterals
    -0.06
    POSITIVE LOGITS
    :Set
    0.07
     tham
    0.07
     realidad
    0.07
     BRE
    0.07
     thematic
    0.07
    	RTDBG
    0.06
     Böl
    0.06
     vyu
    0.06
    .entrySet
    0.06
     urb
    0.06
    Activations Density 0.024%

    No Known Activations