© 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. 89864
    Prev
    Next
    INDEX
    Explanations

    opt out

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect opt-out or unsubscribe options in 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
     tyres
    -0.07
    ("<
    -0.06
     _(
    -0.06
     molec
    -0.06
    sector
    -0.06
     programmes
    -0.06
    .cn
    -0.06
    _timeout
    -0.06
    .setObjectName
    -0.06
     Productions
    -0.06
    POSITIVE LOGITS
     расп
    0.06
    턴
    0.06
    čních
    0.06
     výsled
    0.06
     Phó
    0.06
     ansch
    0.06
    .S
    0.06
     writable
    0.06
    fragistics
    0.06
    Disclosure
    0.06
    Activations Density 0.011%

    No Known Activations