© 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. 42522
    Prev
    Next
    INDEX
    Explanations

    Inability to do something

    np_max-act · gemini-2.0-flash

    information related to schedules or appointments.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron finds is phrases expressing inability or unavailability to attend or make an event (e.g. “can’t attend,” “cannot make it”).

    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
     Rotary
    -0.07
    edics
    -0.07
     cycles
    -0.07
     wäre
    -0.07
    ary
    -0.06
    됩니다
    -0.06
    optional
    -0.06
    go
    -0.06
    ient
    -0.06
     europe
    -0.06
    POSITIVE LOGITS
    xAD
    0.06
     مشکل
    0.06
     walkers
    0.06
     GG
    0.06
     �
    0.06
     outras
    0.06
     현
    0.06
     duel
    0.06
     lø
    0.06
     aktivit
    0.05
    Activations Density 0.044%

    No Known Activations