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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 109551
    Prev
    Next
    INDEX
    Explanations

    warp

    np_max-act · gemini-2.0-flash

    the main thing this neuron does is find mentions of warping or distortion (i.e. material deformation).

    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
    ítica
    -0.07
    nodiscard
    -0.06
     мала
    -0.06
      		
    -0.06
    
    -0.06
    itness
    -0.06
    duğunu
    -0.06
     finalist
    -0.06
    _delegate
    -0.06
     subtree
    -0.06
    POSITIVE LOGITS
     warp
    0.10
     warped
    0.10
    flip
    0.08
     Warp
    0.07
    arp
    0.07
     Harper
    0.07
    प
    0.07
    Pack
    0.07
    pe
    0.07
     bip
    0.07
    Activations Density 0.001%

    No Known Activations