© 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. 89028
    Prev
    Next
    INDEX
    Explanations

    AWS ARN identifier

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of AWS ARNs (tokens forming “arn:aws:…” resource identifier strings).

    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
     Cable
    -0.07
     Hồ
    -0.06
    lédl
    -0.06
     усп
    -0.06
     pdu
    -0.06
     hled
    -0.06
    otřeb
    -0.06
     pomoc
    -0.06
    _pct
    -0.06
    日の
    -0.06
    POSITIVE LOGITS
    stantial
    0.07
    mk
    0.07
    �
    0.07
    ‌ان
    0.07
     constituted
    0.07
    (asset
    0.07
    _COMPONENT
    0.07
     altında
    0.07
    ॉर
    0.06
     solidity
    0.06
    Activations Density 0.002%

    No Known Activations