© 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. 19-RESID-POST-AA
    11. 9040
    Prev
    Next
    INDEX
    Explanations

    Stretch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     edible
    -0.09
     Dios
    -0.06
     empir
    -0.06
    _erase
    -0.06
    Beer
    -0.06
     bunları
    -0.06
    <KeyValuePair
    -0.06
     Orr
    -0.06
     гід
    -0.06
     Lois
    -0.06
    POSITIVE LOGITS
     stretch
    0.10
     stretches
    0.08
     Sprint
    0.08
     stretching
    0.08
    Stretch
    0.08
    _REST
    0.08
     stretched
    0.07
    stretch
    0.07
     Stretch
    0.07
     Sink
    0.07
    Activations Density 0.006%

    No Known Activations