© 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. 91468
    Prev
    Next
    INDEX
    Explanations

    code, color codes

    np_max-act · gemini-2.0-flash

    The neuron is detecting the hexadecimal components (digits/letters) of CSS color codes.

    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
    만남
    -0.07
    _ENDPOINT
    -0.06
     společnost
    -0.06
    ERTICAL
    -0.06
     Engineer
    -0.06
     vot
    -0.06
    playlist
    -0.06
     }(
    -0.06
    @end
    -0.06
     mek
    -0.06
    POSITIVE LOGITS
     Smash
    0.07
     tinh
    0.07
    incerely
    0.07
    stairs
    0.06
     aerobic
    0.06
    	dataType
    0.06
     فع
    0.06
    	sound
    0.06
    	Run
    0.06
    berry
    0.06
    Activations Density 0.005%

    No Known Activations