© 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. 90702
    Prev
    Next
    INDEX
    Explanations

    vessel

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “vessel” (and its plural forms) in the medical text.

    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
    (FALSE
    -0.08
    43
    -0.07
     orange
    -0.07
     Drake
    -0.07
     Latino
    -0.07
    True
    -0.07
     France
    -0.07
    Orange
    -0.07
    _Long
    -0.07
     Try
    -0.06
    POSITIVE LOGITS
     vessel
    0.15
     vessels
    0.13
    essel
    0.10
    سل
    0.08
    sel
    0.08
    στ
    0.07
    ov
    0.07
     �
    0.07
     vess
    0.07
    ess
    0.07
    Activations Density 0.003%

    No Known Activations