© 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. 109430
    Prev
    Next
    INDEX
    Explanations

    thread

    np_max-act · gemini-2.0-flash

    The neuron detects log‐file thread identifiers and their numeric pool/thread naming patterns (e.g., “pool-33-thread-1”).

    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
    _prime
    -0.07
    beer
    -0.07
     overlays
    -0.06
     budete
    -0.06
    fifo
    -0.06
    半
    -0.06
    VBoxLayout
    -0.06
     dend
    -0.06
     показ
    -0.06
    .;.;.;.;
    -0.06
    POSITIVE LOGITS
    �
    0.07
    opup
    0.07
    ляв
    0.06
    	Test
    0.06
     Lug
    0.06
    /{{
    0.06
    sofar
    0.06
    annya
    0.06
    onent
    0.06
    روه
    0.06
    Activations Density 0.005%

    No Known Activations