© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8955
    Prev
    Next
    INDEX
    Explanations

    strange

    np_max-act · gemini-2.0-flash

    The neuron detects the word “Strange,” especially when it appears as a standalone title or heading.

    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
    Potential
    -0.07
    Pi
    -0.07
     Exec
    -0.07
    Lit
    -0.07
    VS
    -0.07
     Vincent
    -0.07
     Lit
    -0.07
     Millennium
    -0.07
    Wilson
    -0.07
    It
    -0.06
    POSITIVE LOGITS
     Strange
    0.11
     strange
    0.10
     stranger
    0.09
     strang
    0.08
     strangers
    0.08
     �
    0.08
    �
    0.08
    Strange
    0.08
     Stranger
    0.07
    reste
    0.07
    Activations Density 0.007%

    No Known Activations