© 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 EvalsExportsinterp-engineNEWAPI 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. 102192
    Prev
    Next
    INDEX
    Explanations

    beros

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of Kerberos‐style network authentication (e.g. SPNEGO/Negotiate and related libraries).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical terms and components related to Kerberos authentication.

    oai_token-act-pair · gpt-4o-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
    ادر
    -0.06
    ยา
    -0.06
    	lock
    -0.06
    andr
    -0.06
     sass
    -0.06
    .bulk
    -0.06
     pity
    -0.06
     highlights
    -0.05
    �
    -0.05
    +"'
    -0.05
    POSITIVE LOGITS
     Pods
    0.07
     finishing
    0.07
    beros
    0.07
    <Field
    0.07
     fyz
    0.07
     DEF
    0.07
    acob
    0.06
     recib
    0.06
     exagger
    0.06
     obtener
    0.06
    Activations Density 0.004%

    No Known Activations