© 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. 100052
    Prev
    Next
    INDEX
    Explanations

    la

    np_max-act · gemini-2.0-flash

    content related to historical and cultural transformations.

    oai_token-act-pair · gpt-4o-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
     on
    -0.07
     Quinn
    -0.06
    aunch
    -0.06
     Budd
    -0.06
     pun
    -0.06
     Hunt
    -0.06
     astronomy
    -0.06
     On
    -0.06
    _Of
    -0.06
    	except
    -0.06
    POSITIVE LOGITS
     la
    0.12
    la
    0.09
    ل
    0.08
    le
    0.08
     the
    0.08
     las
    0.07
     el
    0.07
     La
    0.07
     
    0.07
    الس
    0.07
    Activations Density 0.275%

    No Known Activations