© 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
    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. 93590
    Prev
    Next
    INDEX
    Explanations

    error messages and code

    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
     pravidel
    -0.07
    istros
    -0.07
    ={<
    -0.07
     poc
    -0.06
    	friend
    -0.06
     offense
    -0.06
    fault
    -0.06
     discarded
    -0.06
    :convert
    -0.06
    -derived
    -0.06
    POSITIVE LOGITS
     exactly
    0.07
     Specifies
    0.06
    num
    0.06
    .SelectedIndex
    0.06
    空
    0.06
     pills
    0.06
     cryptography
    0.06
     ADVISED
    0.06
     competed
    0.06
     "__
    0.06
    Activations Density 0.002%

    No Known Activations