© 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. 12704
    Prev
    Next
    INDEX
    Explanations

    left to right

    np_max-act · gemini-2.0-flash

    This neuron detects phrases that describe directional or spatial traversal sequences (e.g. “left to right,” “top to bottom,” “right to left”).

    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
     byte
    -0.07
     settles
    -0.07
    ammo
    -0.06
    Lemma
    -0.06
    invite
    -0.06
    	frame
    -0.06
     σύν
    -0.06
     Heather
    -0.06
     Barang
    -0.06
    ่อง
    -0.06
    POSITIVE LOGITS
    [q
    0.07
    /fast
    0.07
    þ
    0.06
    zimmer
    0.06
     Annotation
    0.06
     diagn
    0.06
     bast
    0.06
     superiority
    0.06
    !=(
    0.06
     hypoc
    0.06
    Activations Density 0.007%

    No Known Activations