© 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. 7863
    Prev
    Next
    INDEX
    Explanations

    harmful

    np_max-act · gemini-2.0-flash

    The neuron detects strongly charged “harm”-related or negative content descriptors (e.g. harmful, toxic, offensive, inappropriate, dangerous).

    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
    .RowStyles
    -0.07
     decoder
    -0.06
     expecting
    -0.06
    \Collections
    -0.06
    culator
    -0.06
    ursday
    -0.06
     trie
    -0.06
    ्दर
    -0.06
     turbulence
    -0.06
     matchmaking
    -0.05
    POSITIVE LOGITS
    nv
    0.07
     Ζ
    0.07
     programme
    0.06
    paren
    0.06
     سلام
    0.06
    setting
    0.06
     PHP
    0.06
     UAE
    0.06
     Injury
    0.06
     trustee
    0.06
    Activations Density 0.021%

    No Known Activations