© 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. 91961
    Prev
    Next
    INDEX
    Explanations

    ial

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “familial,” i.e. the adjective marking a hereditary or family‐related context.

    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
     teg
    -0.07
     Heights
    -0.07
     Both
    -0.07
    Watch
    -0.06
    Playing
    -0.06
    呀
    -0.06
    465
    -0.06
    icated
    -0.06
    _old
    -0.06
     Baş
    -0.06
    POSITIVE LOGITS
     familial
    0.09
     Spiritual
    0.07
     accessibility
    0.07
     cultural
    0.07
    .Font
    0.06
    .Serializable
    0.06
     Salvation
    0.06
     loving
    0.06
     confidentiality
    0.06
     onAnimation
    0.06
    Activations Density 0.001%

    No Known Activations