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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 38754
    Prev
    Next
    INDEX
    Explanations

    architectures

    np_max-act · gemini-2.0-flash

    The neuron activates on CPU architecture and platform identifiers (e.g. ARM, AArch64, MIPS, PPC, RISC, SPARC, x86, etc.).

    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
     hygiene
    -0.07
    tual
    -0.06
    ünüz
    -0.06
    ترك
    -0.06
    /customer
    -0.06
    _mut
    -0.06
    icine
    -0.06
     android
    -0.06
     Qualität
    -0.06
    ytut
    -0.06
    POSITIVE LOGITS
     vowel
    0.09
    δρο
    0.08
     εισ
    0.07
    �
    0.06
     GenerationType
    0.06
    spin
    0.06
    <y
    0.06
     reused
    0.06
    號
    0.06
     aquatic
    0.06
    Activations Density 0.008%

    No Known Activations