© 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. 763
    Prev
    Next
    INDEX
    Explanations

    the letter

    np_max-act · gemini-2.0-flash

    This neuron picks out Python instance‐attribute tokens—especially `self.` attribute names and the `__init__` constructor signature.

    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
     JSImport
    -0.08
    Dll
    -0.07
     BORDER
    -0.07
    شة
    -0.06
    valu
    -0.06
    oğan
    -0.06
     Blob
    -0.06
    وتر
    -0.06
    }*/↵
    -0.06
     necesita
    -0.06
    POSITIVE LOGITS
     commencement
    0.06
     critique
    0.06
     semi
    0.06
    air
    0.06
    _cfg
    0.06
    .grad
    0.06
     Initial
    0.06
    .support
    0.06
    .phi
    0.06
     define
    0.06
    Activations Density 0.005%

    No Known Activations