© 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. 13508
    Prev
    Next
    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting reference or citation markers (e.g., bracketed bibliographic entries).

    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
     reporter
    -0.06
     люд
    -0.06
     символ
    -0.06
    .�
    -0.06
     ICMP
    -0.06
     reife
    -0.06
     kỳ
    -0.06
     taşın
    -0.06
    _CNT
    -0.06
     último
    -0.06
    POSITIVE LOGITS
    \v
    0.07
     excessive
    0.07
                          ↵
    0.06
    scala
    0.06
    .errors
    0.06
     AO
    0.06
     getType
    0.06
    rv
    0.06
    .handleSubmit
    0.06
    .getLongitude
    0.06
    Activations Density 0.008%

    No Known Activations