© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43438
    Prev
    Next
    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash

    mathematical terms and operations involving prime and composite numbers.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to numeric literals, i.e. it activates on tokens representing numbers.

    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
     murderer
    -0.07
     beams
    -0.07
     Patent
    -0.07
    "a
    -0.07
    	arr
    -0.07
    yahoo
    -0.07
     天
    -0.07
     land
    -0.06
    '
    -0.06
     abstract
    -0.06
    POSITIVE LOGITS
    _met
    0.07
    [string
    0.07
    complexType
    0.06
    法律
    0.06
    Sdk
    0.06
     belang
    0.06
     resembling
    0.06
    _HAL
    0.06
    _workflow
    0.06
     logfile
    0.06
    Activations Density 0.020%

    No Known Activations