© 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. 6740
    Prev
    Next
    INDEX
    Explanations

    again

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric tokens—particularly floating‐point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     Polit
    -0.07
    Body
    -0.07
    402
    -0.07
     p
    -0.07
     Soc
    -0.07
    Pizza
    -0.07
    Motor
    -0.07
     Smy
    -0.07
     competency
    -0.07
    Sk
    -0.07
    POSITIVE LOGITS
     again
    0.16
    again
    0.11
     Again
    0.10
     wieder
    0.08
    -END
    0.08
    aneously
    0.08
     AGAIN
    0.08
    番
    0.08
     yeniden
    0.08
     back
    0.08
    Activations Density 0.016%

    No Known Activations