© 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. 91663
    Prev
    Next
    INDEX
    Explanations

    technical text

    np_max-act · gemini-2.0-flash

    The neuron is strongly activated by numeric tokens representing decimal fractions (i.e. numbers containing a “.”).

    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
    :'
    -0.07
    pur
    -0.07
    머니
    -0.06
    że
    -0.06
     Ấ
    -0.06
    Los
    -0.06
     지원
    -0.06
    助
    -0.06
    evity
    -0.06
    -align
    -0.06
    POSITIVE LOGITS
    ROME
    0.07
    _ASSOC
    0.07
    ane
    0.06
     Interested
    0.06
    _mr
    0.06
     brain
    0.06
     av
    0.06
     Av
    0.06
     Trav
    0.06
    wrapper
    0.06
    Activations Density 0.000%

    No Known Activations