© 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. 88263
    Prev
    Next
    INDEX
    Explanations

    uptake

    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_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
    isor
    -0.07
    jíž
    -0.07
     friendship
    -0.06
    _friend
    -0.06
    Dim
    -0.06
    Pos
    -0.06
     گرد
    -0.06
    DIS
    -0.06
    CONST
    -0.06
     Sig
    -0.06
    POSITIVE LOGITS
     uptake
    0.14
     rates
    0.08
     Ottawa
    0.07
     uplift
    0.07
    交通
    0.07
     adopts
    0.07
     uplifting
    0.07
     vaping
    0.07
     Öğren
    0.07
     χρή
    0.07
    Activations Density 0.003%

    No Known Activations