© 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. 52161
    Prev
    Next
    INDEX
    Explanations

    the

    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
    .Tab
    -0.06
    @Before
    -0.06
     lành
    -0.06
     Guild
    -0.06
     EN
    -0.06
    배
    -0.06
     Tel
    -0.06
     Υπο
    -0.06
     nap
    -0.05
    Lng
    -0.05
    POSITIVE LOGITS
     Recursive
    0.07
    chunks
    0.07
     indispens
    0.06
    <dyn
    0.06
    FieldType
    0.06
     ticking
    0.06
     imperative
    0.06
     Dependencies
    0.06
    	sum
    0.06
    )?;↵
    0.06
    Activations Density 0.008%

    No Known Activations