© 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. 27424
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    references to fictional characters associated with significant destruction or villainy.

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

    The neuron detects special metadata or header tokens marking the start of an assistant’s response (e.g. “<|start_header_id|>” and related header fields).

    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
     gorge
    -0.07
     Agency
    -0.06
    FileType
    -0.06
    ريم
    -0.06
     LEDs
    -0.06
    .fix
    -0.06
    医院
    -0.06
    .ud
    -0.06
    Development
    -0.06
    Salt
    -0.06
    POSITIVE LOGITS
     rond
    0.07
     (!
    0.07
     souha
    0.06
     █
    0.06
    !
    0.06
     równ
    0.06
     مطرح
    0.06
    HasBeenSet
    0.06
    !="
    0.06
     которая
    0.06
    Activations Density 0.046%

    No Known Activations