© 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 EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 92937
    Prev
    Next
    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash

    The neuron detects JSON-formatted output (especially the closing brace/end of a JSON object).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    383
    -0.07
     Pred
    -0.07
    392
    -0.07
     marsh
    -0.06
       
    -0.06
     learn
    -0.06
     Bah
    -0.06
     Friedman
    -0.06
    英语
    -0.06
    forums
    -0.06
    POSITIVE LOGITS
    Ě
    0.08
    }
    0.07
    ị
    0.07
     JObject
    0.07
    }?
    0.07
    >();
    0.07
    >}
    0.07
    AllArgsConstructor
    0.07
    <?>>
    0.06
    	loop
    0.06
    Activations Density 0.013%

    No Known Activations