© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 112096
    Prev
    Next
    INDEX
    Explanations

    close

    np_max-act · gemini-2.0-flash

    Instances where the text expresses a comparison indicating one thing approximates or resembles another (phrases that say one thing is the closest/most similar to something).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ỏ
    -0.07
     тор
    -0.06
     Rede
    -0.06
    sob
    -0.06
     renew
    -0.06
     Portuguese
    -0.06
     Tek
    -0.06
     multif
    -0.06
     Mid
    -0.06
     operational
    -0.06
    POSITIVE LOGITS
     regress
    0.07
     khuôn
    0.07
    界
    0.07
    なんだ
    0.07
     getData
    0.07
    opsis
    0.07
    覆
    0.06
     sugars
    0.06
    еної
    0.06
    ीड
    0.06
    Activations Density 0.014%

    No Known Activations