© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126106
    Prev
    Next
    INDEX
    Explanations

    Border security

    np_max-act · gemini-2.0-flash

    The neuron activates on words related to border or security screening procedures (e.g. officers, passport, security, search).

    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
    OR
    -0.07
     cell
    -0.07
     Bol
    -0.07
    _DETECT
    -0.06
     visitors
    -0.06
    类型
    -0.06
     Cell
    -0.06
     monster
    -0.06
     WHITE
    -0.06
    Else
    -0.06
    POSITIVE LOGITS
    ]:=
    0.08
     исч
    0.07
     그래
    0.06
     báo
    0.06
     spotify
    0.06
     sudah
    0.06
    \AppData
    0.06
     doğal
    0.06
     قدر
    0.06
    iến
    0.06
    Activations Density 0.028%

    No Known Activations