© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73820
    Prev
    Next
    INDEX
    Explanations

    tunnel

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of “tunnel” (and its morphological variants like “tunnelling” or “tunneling”).

    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
    signature
    -0.07
     specification
    -0.07
    �
    -0.07
     ate
    -0.07
    /database
    -0.07
    Sch
    -0.07
    libc
    -0.06
     Poor
    -0.06
     spicy
    -0.06
     preference
    -0.06
    POSITIVE LOGITS
     행동
    0.06
     talks
    0.06
     "";
    0.06
     behaviors
    0.06
    aggable
    0.06
    cratch
    0.06
     teleport
    0.06
    .setLocation
    0.06
     determined
    0.06
     blames
    0.06
    Activations Density 0.001%

    No Known Activations