© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 104673
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    Activation
    -0.07
     Rule
    -0.07
     conjunction
    -0.07
    िल
    -0.07
     performance
    -0.06
     Buddy
    -0.06
     tonight
    -0.06
     ">
    -0.06
    patrick
    -0.06
    .!
    -0.06
    POSITIVE LOGITS
    WEEN
    0.07
     theolog
    0.06
     중요한
    0.06
     stál
    0.06
     GMO
    0.06
     aliqua
    0.06
     reimbursement
    0.06
    νος
    0.06
     hv
    0.06
     đau
    0.06
    Activations Density 0.237%

    No Known Activations