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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1097
    Prev
    Next
    INDEX
    Explanations

    race

    np_max-act · gemini-2.0-flash

    references to racial or ethnic identity.

    oai_token-act-pair · gpt-4oTriggered by @tcai

    This neuron activates on French-language words and phrases.

    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
    orsi
    -0.07
    FFT
    -0.06
     cortex
    -0.06
    _VARS
    -0.06
     Shore
    -0.06
    .cs
    -0.06
    PEC
    -0.06
    提供
    -0.06
    pec
    -0.06
    成人
    -0.06
    POSITIVE LOGITS
    --------------↵
    0.07
    кет
    0.06
     friends
    0.06
    ='')↵
    0.06
    _help
    0.06
    .fileName
    0.06
    	IN
    0.06
    UNCTION
    0.06
    layers
    0.06
     spontaneous
    0.06
    Activations Density 0.018%

    No Known Activations