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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 20975
    Prev
    Next
    INDEX
    Explanations

    path

    np_max-act · gemini-2.0-flash

    programming-related terms and concepts associated with software licensing and public licenses.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron flags occurrences of the “Classpath exception” license phrase (i.e. the word “path” in the “Class path exception” header comment).

    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
    Fabric
    -0.08
     beans
    -0.07
     descendants
    -0.07
    setOnClickListener
    -0.07
    FDA
    -0.06
     شدن
    -0.06
    شار
    -0.06
    Digest
    -0.06
    wt
    -0.06
     گفته
    -0.06
    POSITIVE LOGITS
    ighter
    0.08
    ollapse
    0.07
     aesthetic
    0.06
    ,color
    0.06
    äl
    0.06
     autob
    0.06
     hum
    0.06
     مز
    0.06
     İngiliz
    0.06
    (gc
    0.06
    Activations Density 0.000%

    No Known Activations