© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68853
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions using methods

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens and decimal measurements (e.g. “1.62109375,” “2.09765625,” “400 nm,” etc.).

    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
    "]).
    -0.08
    "].
    -0.07
     diplomats
    -0.07
    Broadcast
    -0.07
     Else
    -0.07
    ‌ان
    -0.06
     dzi
    -0.06
     Broadcast
    -0.06
     content
    -0.06
    Bindings
    -0.06
    POSITIVE LOGITS
     chăm
    0.06
    lasyon
    0.06
     pří
    0.06
    ivement
    0.06
    )",
↵
    0.06
    _DM
    0.06
    _STS
    0.06
    /drivers
    0.06
    .JComboBox
    0.06
    _priv
    0.06
    Activations Density 0.057%

    No Known Activations