Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 40505
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    names of individuals associated with Australian rules football.

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

    This neuron flags bibliographic reference entries, especially the “Encyclopedia of …” citation lines.

    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
     tempered
    -0.07
     alkal
    -0.07
    USA
    -0.07
     sites
    -0.07
     ads
    -0.07
    'Neill
    -0.06
     сіль
    -0.06
    _memory
    -0.06
     підприємств
    -0.06
    war
    -0.06
    POSITIVE LOGITS
    $page
    0.06
     satisfactory
    0.06
    >{{$
    0.06
    fieldName
    0.06
    %',
    0.06
     cupboard
    0.06
    $return
    0.06
    oined
    0.06
    spawn
    0.05
     weir
    0.05
    Activations Density 0.008%

    No Known Activations