Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 45285
    Prev
    Next
    INDEX
    Explanations

    what

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     believable
    -0.07
    	mouse
    -0.06
     SUCCESS
    -0.06
    dda
    -0.06
    __["
    -0.06
     FALSE
    -0.06
    Easy
    -0.06
    <Boolean
    -0.06
     branching
    -0.06
     headlines
    -0.06
    POSITIVE LOGITS
     inters
    0.07
    各种
    0.07
     bouquet
    0.07
         
    0.07
     اصل
    0.06
    币
    0.06
    /var
    0.06
    .drawString
    0.06
    ารถ
    0.06
    HR
    0.06
    Activations Density 0.031%

    No Known Activations