© 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. 13092
    Prev
    Next
    INDEX
    Explanations

    too

    np_max-act · gemini-2.0-flash

    The neuron detects the warning‐of‐doom phrase “it was too late.”

    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
     MJ
    -0.07
    .yang
    -0.07
     μόνο
    -0.06
     günü
    -0.06
    .dat
    -0.06
     standby
    -0.06
    制作
    -0.06
     Memories
    -0.06
     سرعت
    -0.06
     soutěže
    -0.06
    POSITIVE LOGITS
     tabIndex
    0.06
     comprend
    0.06
    ->{_
    0.06
     Amendment
    0.06
    $search
    0.06
    plaint
    0.06
    licting
    0.06
     qed
    0.06
    poster
    0.06
    weathermap
    0.06
    Activations Density 0.010%

    No Known Activations