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. 130663
    Prev
    Next
    INDEX
    Explanations

    pieces

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of “puzzle,” “pieces,” and “together,” effectively detecting puzzle‐assembly metaphors.

    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
    SizeMode
    -0.07
     screen
    -0.07
    [layer
    -0.06
     nasty
    -0.06
     ctype
    -0.06
    uri
    -0.06
    ू
    -0.06
    .getPath
    -0.06
    ::$
    -0.06
    \xff
    -0.06
    POSITIVE LOGITS
     conosc
    0.08
    igsaw
    0.07
    CLAIM
    0.07
    �合
    0.07
    	CC
    0.07
    ้าย
    0.06
     FUNC
    0.06
    ($__
    0.06
    .Tasks
    0.06
     possibile
    0.06
    Activations Density 0.009%

    No Known Activations