Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 127462
    Prev
    Next
    INDEX
    Explanations

    book reviews

    np_max-act · gemini-2.0-flash

    This neuron detects subjective, evaluative language—especially words expressing personal emotions or opinions in reviews.

    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
    ��
    -0.07
    acho
    -0.06
     terror
    -0.06
     estimation
    -0.06
     grille
    -0.06
     Deutsch
    -0.06
    quets
    -0.06
     engine
    -0.06
     killer
    -0.06
     peptide
    -0.06
    POSITIVE LOGITS
    _INTR
    0.06
    _do
    0.06
     �
    0.06
    _ai
    0.06
    دام
    0.06
     �
    0.06
    �
    0.06
     зм
    0.06
    istency
    0.06
     Toggle
    0.05
    Activations Density 0.028%

    No Known Activations