© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68709
    Prev
    Next
    INDEX
    Explanations

    retain

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the “retain/retention/retaining” family of words, flagging mentions of holding, keeping, or preserving something.

    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
    窗
    -0.07
    冬
    -0.07
     Playground
    -0.07
     playground
    -0.07
     plaza
    -0.07
     Circle
    -0.07
    	dfs
    -0.07
     hill
    -0.07
     Weg
    -0.07
    θρώ
    -0.07
    POSITIVE LOGITS
     retain
    0.11
     retention
    0.11
     retained
    0.10
     retains
    0.10
     retaining
    0.09
     Ret
    0.08
    -results
    0.07
     latent
    0.07
     gaining
    0.07
     Req
    0.07
    Activations Density 0.007%

    No Known Activations