© 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. 110122
    Prev
    Next
    INDEX
    Explanations

    things

    np_max-act · gemini-2.0-flash

    The neuron activates on the occurrence of the word “things,” marking generic “things” placeholders in a sentence.

    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
    Overlap
    -0.07
    �
    -0.07
    	usage
    -0.06
    HeadersHeight
    -0.06
     گ
    -0.06
     موج
    -0.06
    请输入
    -0.06
    .Tween
    -0.06
    ,np
    -0.06
    .getPort
    -0.06
    POSITIVE LOGITS
     things
    0.09
     Things
    0.08
    >↵↵
    0.07
     cosas
    0.07
    conditions
    0.07
    ी।↵
    0.07
    たり
    0.07
     stuff
    0.06
    LIGHT
    0.06
    krát
    0.06
    Activations Density 0.027%

    No Known Activations