© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7871
    Prev
    Next
    INDEX
    Explanations

    SHALL

    np_max-act · gemini-2.0-flash

    classes and interfaces related to requesting and managing building data.

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

    The neuron is detecting the occurrence of the “IN NO EVENT SHALL” phrase (commonly part of software license disclaimer text).

    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
    .FlatAppearance
    -0.07
    CAS
    -0.07
    _Enter
    -0.06
    Known
    -0.06
     isVisible
    -0.06
     oferta
    -0.06
     рецеп
    -0.06
     الکترون
    -0.06
    (DateTime
    -0.06
    maintenance
    -0.06
    POSITIVE LOGITS
     SHALL
    0.08
     shall
    0.06
    ll
    0.06
     forth
    0.06
     superClass
    0.06
    .readyState
    0.06
     Godzilla
    0.06
     worthless
    0.06
    -ui
    0.06
     subway
    0.06
    Activations Density 0.001%

    No Known Activations