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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 122790
    Prev
    Next
    INDEX
    Explanations

    };

    np_max-act · gemini-2.0-flash

    JavaScript functions related to date pickers in multiple languages.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on the punctuation‐heavy bits of JavaScript code—tokens like “;”, “.”, “=”, “{”, “$(” and similar syntax elements.

    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
     minValue
    -0.07
    .resp
    -0.07
     MHz
    -0.07
    .bl
    -0.07
     هاي
    -0.07
    	is
    -0.06
     알
    -0.06
     �
    -0.06
     padd
    -0.06
    IFA
    -0.06
    POSITIVE LOGITS
     ")"↵
    0.06
    />↵↵
    0.06
     Bowling
    0.06
     Weapon
    0.06
     antibiotic
    0.06
     diagrams
    0.06
    çuk
    0.06
     Dustin
    0.06
    وي
    0.06
    entered
    0.06
    Activations Density 0.003%

    No Known Activations