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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 84646
    Prev
    Next
    INDEX
    Explanations

    –

    np_max-act · gemini-2.0-flash

    The neuron detects numeric date information—specifically year values and year‐range notations (e.g., birth–death years) often shown in parentheses.

    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
     readonly
    -0.06
    aw
    -0.06
    聞
    -0.06
    	env
    -0.06
    -backed
    -0.06
     blade
    -0.06
    산업
    -0.06
    кол
    -0.06
    _car
    -0.06
    )"↵
    -0.06
    POSITIVE LOGITS
    ře
    0.07
    ournée
    0.07
    іш
    0.06
    _margin
    0.06
     здійснення
    0.06
    Operation
    0.06
     Jedi
    0.06
     Operation
    0.06
     *);↵↵
    0.06
    él
    0.06
    Activations Density 0.009%

    No Known Activations