© 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. 92034
    Prev
    Next
    INDEX
    Explanations

    URLs/Code punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on square‐bracket characters used in markup (e.g. markdown link or list syntax).

    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
     horrend
    -0.06
     als
    -0.06
    ្�
    -0.06
    akah
    -0.06
     horrors
    -0.06
    Jer
    -0.06
     občan
    -0.06
    kad
    -0.06
     hurl
    -0.06
    dae
    -0.06
    POSITIVE LOGITS
     setUsername
    0.07
    *scale
    0.07
     탄
    0.07
     snatch
    0.07
    0.07
    _SS
    0.07
     Tender
    0.07
    'acc
    0.07
    >/
    0.06
     "%
    0.06
    Activations Density 0.000%

    No Known Activations