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. 85956
    Prev
    Next
    INDEX
    Explanations

    -scale

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of “large-scale” (i.e. scale/magnitude descriptors).

    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
     dead
    -0.07
     playlists
    -0.07
     Bad
    -0.06
    _Sub
    -0.06
     الاس
    -0.06
    iders
    -0.06
    	send
    -0.06
    >y
    -0.06
    ød
    -0.06
    357
    -0.05
    POSITIVE LOGITS
    规模
    0.08
    -scale
    0.08
     scale
    0.07
     ascertain
    0.07
     widespread
    0.07
    Licensed
    0.07
    ská
    0.07
     biggest
    0.06
     concerted
    0.06
    _LICENSE
    0.06
    Activations Density 0.005%

    No Known Activations