© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74928
    Prev
    Next
    INDEX
    Explanations

    )-

    np_max-act · gemini-2.0-flash

    technical terms related to chemical reactions and material formation.

    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
     rumor
    -0.07
     akce
    -0.07
    c
    -0.07
     mec
    -0.07
    	sc
    -0.06
     feature
    -0.06
    iqué
    -0.06
     texture
    -0.06
     who
    -0.06
    Comment
    -0.06
    POSITIVE LOGITS
    ()/
    0.10
    )-
    0.09
    ()==
    0.09
    }-
    0.09
    )—
    0.08
    ()+
    0.08
    +","+
    0.08
    )/
    0.08
     Californ
    0.08
    だから
    0.08
    Activations Density 0.031%

    No Known Activations