© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128645
    Prev
    Next
    INDEX
    Explanations

    Code/programming text

    np_max-act · gemini-2.0-flash

    This neuron is essentially “dead” and does not detect any patterns (it never activates).

    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
     EventType
    -0.06
     entityManager
    -0.06
    .swt
    -0.06
     Kat
    -0.06
    .Compute
    -0.06
     LEFT
    -0.06
     NIL
    -0.06
    스템
    -0.06
    "])
    -0.06
     immun
    -0.06
    POSITIVE LOGITS
    ст
    0.07
    -अ
    0.07
    upaten
    0.07
    )+↵
    0.06
     معل
    0.06
     incid
    0.06
    ünü
    0.06
    )V
    0.06
     uma
    0.06
     neger
    0.06
    Activations Density 0.391%

    No Known Activations