© 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. 92166
    Prev
    Next
    INDEX
    Explanations

    Events

    np_max-act · gemini-2.0-flash

    The neuron fires on temporal/event markers—phrases that locate things in time (e.g. “at the Cannes Film Festival,” “around the time that…was released,” “appeared on…”).

    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
     Color
    -0.07
    ENCH
    -0.07
    çu
    -0.06
     Compile
    -0.06
    drivers
    -0.06
     createDate
    -0.06
     Ps
    -0.06
    ��
    -0.06
     tackles
    -0.06
     PART
    -0.06
    POSITIVE LOGITS
     numberWithInt
    0.07
    )):
    0.06
    ?><
    0.06
    livě
    0.06
    >>↵
    0.06
    //(
    0.06
    mé
    0.06
    riott
    0.06
    .rightBarButtonItem
    0.06
     transaction
    0.06
    Activations Density 0.168%

    No Known Activations