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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 88927
    Prev
    Next
    INDEX
    Explanations

    code/markup

    np_max-act · gemini-2.0-flash

    This neuron detects the special bracketed jailbreak or role-label markers (e.g. “[CLASSIC]”, “[JAILBREAK]”) and related prompt-injection tokens.

    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
    stacles
    -0.06
     scarce
    -0.06
    ुड
    -0.06
    urtles
    -0.06
     CAP
    -0.06
    zego
    -0.06
    ounced
    -0.06
     assertions
    -0.06
    oked
    -0.06
     posture
    -0.06
    POSITIVE LOGITS
     marrow
    0.07
    dT
    0.06
    (blob
    0.06
     davranış
    0.06
     برج
    0.06
     aust
    0.06
     الم
    0.06
    .jsp
    0.06
    _cs
    0.06
    .getChannel
    0.06
    Activations Density 0.006%

    No Known Activations