Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90208
    Prev
    Next
    INDEX
    Explanations

    measurements of speed/distance

    np_max-act · gemini-2.0-flash

    This neuron responds to numerical measurements, particularly speed values and their units.

    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
    croll
    -0.07
    eru
    -0.07
    ::__
    -0.06
    府
    -0.06
    	buff
    -0.06
     webhook
    -0.06
    	node
    -0.06
    irus
    -0.06
    endl
    -0.06
    -copy
    -0.06
    POSITIVE LOGITS
     CORPOR
    0.07
     tượng
    0.06
    -serving
    0.06
    AGENT
    0.06
    ATHER
    0.06
     आश
    0.06
    KM
    0.06
    msgid
    0.06
    ।↵
    0.06
     HIP
    0.06
    Activations Density 0.014%

    No Known Activations