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. 40461
    Prev
    Next
    INDEX
    Explanations

    current events

    np_max-act · gemini-2.0-flash

    references to artistic projects, exhibitions, or personal reflections on the creative process.

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

    This neuron activates on references to the current global or social situation—words and phrases describing the state of the world, crises, unrest, or societal turmoil.

    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
    Instrument
    -0.06
    interop
    -0.06
    enne
    -0.06
    극
    -0.06
     lear
    -0.06
    ,不过
    -0.06
    飾
    -0.06
     hypothesis
    -0.06
     KD
    -0.06
    uppen
    -0.06
    POSITIVE LOGITS
    _COR
    0.07
    ORIZ
    0.07
     passed
    0.07
    _ENGINE
    0.07
     dem
    0.07
     O
    0.07
    ADATA
    0.06
    ?>↵↵
    0.06
     volcanic
    0.06
    ancellor
    0.06
    Activations Density 0.044%

    No Known Activations