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. 126960
    Prev
    Next
    INDEX
    Explanations

    override implement

    np_max-act · gemini-2.0-flash

    The neuron detects documentation or comment lines that instruct subclasses (or derived classes) to override or implement specific methods.

    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
    _child
    -0.07
    IV
    -0.07
    ...");↵
    -0.07
    Mob
    -0.06
    uraa
    -0.06
    Usuarios
    -0.06
    <any
    -0.06
    idad
    -0.06
     физ
    -0.06
     آر
    -0.06
    POSITIVE LOGITS
     عملية
    0.06
     Cocktail
    0.06
    celed
    0.06
    不得
    0.06
    缓
    0.06
     ARP
    0.06
    نع
    0.06
    -->
    ↵
    0.06
    sns
    0.06
    分别
    0.06
    Activations Density 0.008%

    No Known Activations