© 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. 51943
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash

    formal patent-style/technical document phrases and section headings introducing the invention or describing the field and methods.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     Collabor
    -0.07
     noct
    -0.07
     ef
    -0.07
     abc
    -0.07
     bv
    -0.06
    DESCRIPTION
    -0.06
     properties
    -0.06
    :'#
    -0.06
    884
    -0.06
    -connect
    -0.06
    POSITIVE LOGITS
    _php
    0.07
     Unity
    0.07
    联网
    0.07
    )sender
    0.07
    (rep
    0.06
     dal
    0.06
     Congo
    0.06
    .Slf
    0.06
    NodeId
    0.06
    Posted
    0.06
    Activations Density 0.144%

    No Known Activations