© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58307
    Prev
    Next
    INDEX
    Explanations

    achieve

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the verb “achieve” in user questions asking how to accomplish something.

    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
     Darkness
    -0.07
     Paz
    -0.07
    on
    -0.07
     Lans
    -0.07
    Mos
    -0.07
    Pod
    -0.07
     lone
    -0.07
    -zone
    -0.07
     Blank
    -0.07
    118
    -0.07
    POSITIVE LOGITS
     achieved
    0.13
     achieve
    0.12
     achievement
    0.11
     achieving
    0.10
     attained
    0.09
     achieves
    0.09
     achievements
    0.08
     дости
    0.08
    AI
    0.08
     이후
    0.08
    Activations Density 0.028%

    No Known Activations