© 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. 8930
    Prev
    Next
    INDEX
    Explanations

    displacement

    np_max-act · gemini-2.0-flash

    terms related to displacement measurements and apparatus in scientific contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects occurrences of the technical term “displacement” (and its compounds) in engineering or scientific contexts.

    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
    or
    -0.08
     novice
    -0.07
     certify
    -0.07
     forwarded
    -0.07
     fprintf
    -0.06
     terrace
    -0.06
    877
    -0.06
    atron
    -0.06
    .run
    -0.06
    ron
    -0.06
    POSITIVE LOGITS
     displacement
    0.14
     displaced
    0.13
     displ
    0.10
    placement
    0.09
    vsp
    0.08
     DISCLAIM
    0.08
    езд
    0.08
    zh
    0.08
    placing
    0.08
    =device
    0.07
    Activations Density 0.004%

    No Known Activations