© 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. 18051
    Prev
    Next
    INDEX
    Explanations

    freedom/rescue

    np_max-act · gemini-2.0-flash

    The neuron activates on words signaling that someone has been released, freed, rescued, or safely returned.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions of abduction and captivity.

    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
    .edu
    -0.07
     cuts
    -0.07
    生き
    -0.07
    _Zero
    -0.06
    ando
    -0.06
    _res
    -0.06
    ../../../
    -0.06
     cloned
    -0.06
     EFF
    -0.06
     Fior
    -0.06
    POSITIVE LOGITS
     ngOnDestroy
    0.07
     recher
    0.06
    .setPosition
    0.06
    Sql
    0.06
    wig
    0.06
    /connection
    0.06
    **,
    0.06
    (datas
    0.06
    ]")]↵
    0.06
     هل
    0.06
    Activations Density 0.016%

    No Known Activations