© 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. 7-RESID-POST-AA
    11. 40582
    Prev
    Next
    INDEX
    Explanations

    of

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iterated
    -0.07
    �i
    -0.06
    peration
    -0.06
    алізації
    -0.06
     mesure
    -0.06
    Ear
    -0.06
    _vp
    -0.06
     Kunst
    -0.06
     Urs
    -0.06
     breath
    -0.06
    POSITIVE LOGITS
     waived
    0.06
     EXISTS
    0.06
     honorable
    0.06
    	Json
    0.06
     esteemed
    0.06
    	Status
    0.06
    .RelativeLayout
    0.06
    Arrange
    0.06
     рань
    0.06
    ;margin
    0.06
    Activations Density 0.042%

    No Known Activations