© 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. 30028
    Prev
    Next
    INDEX
    Explanations

    Constant parameters and comparisons

    np_max-act · gemini-2.0-flash

    The neuron fires on technical numeric measurements—especially floating‐point numbers and precise decimal values.

    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
    _log
    -0.07
    _dispatch
    -0.07
     всього
    -0.07
    .lt
    -0.07
     LGBTQ
    -0.06
    upload
    -0.06
     addSubview
    -0.06
     supermarket
    -0.06
     qa
    -0.06
    	return
    -0.06
    POSITIVE LOGITS
     onLoad
    0.06
     flashed
    0.06
    <()>
    0.06
     заступ
    0.06
     】
    0.06
     Walking
    0.06
     Unified
    0.06
     proh
    0.06
    -------
    0.06
    =batch
    0.06
    Activations Density 0.110%

    No Known Activations