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

    Neuronpedia

    APICircuit 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. 130806
    Prev
    Next
    INDEX
    Explanations

    ma

    np_max-act · gemini-2.0-flash

    The neuron activates on all-caps technical acronyms or abbreviations.

    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
    .dat
    -0.07
    ammad
    -0.06
    	be
    -0.06
    ńst
    -0.06
     DECLARE
    -0.06
     urlparse
    -0.06
     domicile
    -0.06
     canned
    -0.06
    .TextView
    -0.06
    -unused
    -0.06
    POSITIVE LOGITS
     ashes
    0.07
    )↵↵↵↵
    0.07
     icmp
    0.07
    Summary
    0.07
     :↵↵↵↵
    0.06
     resale
    0.06
     "")↵↵
    0.06
     Genetic
    0.06
    ])
    ↵
    ↵
    0.06
     Layers
    0.06
    Activations Density 0.226%

    No Known Activations