© 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. 105159
    Prev
    Next
    INDEX
    Explanations

    instructions and explanations

    np_max-act · gemini-2.0-flash

    aspects related to incident response in cloud engineering.

    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
    (ent
    -0.08
     meta
    -0.07
    _closed
    -0.07
    wan
    -0.07
    平台
    -0.07
     lifespan
    -0.06
     judicial
    -0.06
     handler
    -0.06
     filter
    -0.06
     browsers
    -0.06
    POSITIVE LOGITS
    レイ
    0.06
     g
    0.06
    >>,↵
    0.06
     Wh
    0.06
    ��
    0.06
    ٹ
    0.06
    اا
    0.06
     travail
    0.06
     глиб
    0.06
     griev
    0.06
    Activations Density 0.252%

    No Known Activations