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. 129395
    Prev
    Next
    INDEX
    Explanations

    spectral

    np_max-act · gemini-2.0-flash

    This neuron activates on floating‐point numeric tokens (decimal 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
    Seq
    -0.06
     Ord
    -0.06
    лиш
    -0.06
     rows
    -0.06
    _ht
    -0.06
    _WORDS
    -0.06
     tube
    -0.06
     Canyon
    -0.06
     Festival
    -0.06
    aad
    -0.06
    POSITIVE LOGITS
     ekonom
    0.07
     Recomm
    0.07
     Investig
    0.07
     plaintiffs
    0.06
     plaintiff
    0.06
     stringWithFormat
    0.06
     DBHelper
    0.06
     Michigan
    0.06
     forControlEvents
    0.06
     XPAR
    0.06
    Activations Density 0.004%

    No Known Activations