© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6167
    Prev
    Next
    INDEX
    Explanations

    modification

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the “modif-” stem (e.g. modify, modification, modifying).

    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
     ecosystem
    -0.08
    urray
    -0.08
     Eagle
    -0.07
     culp
    -0.07
     sea
    -0.07
     Campbell
    -0.07
     east
    -0.06
     surpass
    -0.06
     circum
    -0.06
     EnumerableStream
    -0.06
    POSITIVE LOGITS
     Modified
    0.10
     Mod
    0.09
    modifier
    0.09
     modification
    0.09
     modifier
    0.09
     modified
    0.09
    modification
    0.09
    _MOD
    0.09
     mod
    0.08
     modifications
    0.08
    Activations Density 0.027%

    No Known Activations