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

    Neuronpedia

    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. 128256
    Prev
    Next
    INDEX
    Explanations

    beta

    np_max-act · gemini-2.0-flash

    keywords related to Kubernetes API definitions and resource expansion types.

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

    The neuron fires on “alpha” or “beta” tokens in version strings (e.g. API version qualifiers like v1alpha1 or v1beta2).

    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
     erreur
    -0.06
    ΟΣ
    -0.06
     incontr
    -0.06
    ｝
    -0.06
     нічого
    -0.06
    Entry
    -0.06
     viscosity
    -0.06
     несп
    -0.06
    _prec
    -0.06
     cen
    -0.06
    POSITIVE LOGITS
     品
    0.07
    PasswordEncoder
    0.07
    aban
    0.07
     Alex
    0.07
     освіти
    0.07
    乃
    0.07
    .urlencoded
    0.07
     suspects
    0.07
    .telegram
    0.06
    妈
    0.06
    Activations Density 0.000%

    No Known Activations