© 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. 30570
    Prev
    Next
    INDEX
    Explanations

    knockout

    np_max-act · gemini-2.0-flash

    The neuron detects references to gene‐ or protein‐inactivation experiments, especially “knockout”/“KO” mentions.

    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
     majestic
    -0.08
     shore
    -0.07
     política
    -0.07
     volatile
    -0.06
     베스트
    -0.06
    _asc
    -0.06
     allotted
    -0.06
     nose
    -0.06
    anne
    -0.06
     battery
    -0.06
    POSITIVE LOGITS
     renovated
    0.07
     knockout
    0.07
    groundColor
    0.07
    backs
    0.07
     А
    0.07
     صاح
    0.06
    oubted
    0.06
     revamped
    0.06
    。",↵
    0.06
     annihil
    0.06
    Activations Density 0.006%

    No Known Activations