© 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
    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. 6548
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    narratives that evoke personal and emotional connections to experiences.

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

    The neuron detects expressions indicating that something lingers in one’s mind or memory (e.g. “stuck with me,” “stayed with me long after”).

    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
    .(
    -0.06
     부
    -0.06
     admit
    -0.06
    .find
    -0.06
    ("$.
    -0.06
    (token
    -0.06
     thỏa
    -0.06
     linkage
    -0.06
    CONF
    -0.06
    _FRE
    -0.06
    POSITIVE LOGITS
    akens
    0.07
     unut
    0.07
    θρω
    0.06
    rière
    0.06
     характ
    0.06
     lég
    0.06
    द
    0.06
    uchar
    0.06
     ihtiyaç
    0.06
     Ottawa
    0.06
    Activations Density 0.013%

    No Known Activations