© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109246
    Prev
    Next
    INDEX
    Explanations

    conver

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “Cauchy sequences” (i.e. the term “Cauchy-sequence” and its occurrence in convergence statements).

    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
     SW
    -0.07
    าคม
    -0.06
     свои
    -0.06
    ิทยา
    -0.06
    "
↵
↵
    -0.06
    東京
    -0.06
     params
    -0.06
    ronym
    -0.05
     INIT
    -0.05
    обов
    -0.05
    POSITIVE LOGITS
    /Runtime
    0.07
    .Client
    0.07
     regimen
    0.07
     deviceId
    0.07
    pesan
    0.06
     UserModel
    0.06
    053
    0.06
    _way
    0.06
    .Alter
    0.06
     branch
    0.06
    Activations Density 0.004%

    No Known Activations