© 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. 91467
    Prev
    Next
    INDEX
    Explanations

    ^

    np_max-act · gemini-2.0-flash

    This neuron does not consistently activate for any particular token sequence and appears not to detect any specific pattern.

    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
     Atlantis
    -0.07
    Traffic
    -0.06
    _CPP
    -0.06
    22
    -0.06
    ворю
    -0.06
     canActivate
    -0.06
    doctrine
    -0.06
    clared
    -0.06
    stacles
    -0.06
    уются
    -0.06
    POSITIVE LOGITS
     innoc
    0.07
    -mask
    0.07
     фай
    0.07
     stitched
    0.06
    	restore
    0.06
     sounded
    0.06
    彩
    0.06
     chiếc
    0.06
    .....
    0.06
    جع
    0.06
    Activations Density 0.025%

    No Known Activations