© 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. 7-RESID-POST-AA
    11. 112468
    Prev
    Next
    INDEX
    Explanations

    online assistance and support

    np_max-act · gemini-2.0-flash

    markers indicating the assistant’s role/turn in chat-style conversation metadata.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Enjoy
    -0.07
     stor
    -0.07
    recall
    -0.06
     MutableLiveData
    -0.06
    Context
    -0.06
    ]';↵
    -0.06
    是在
    -0.06
     StringSplitOptions
    -0.06
    \Traits
    -0.06
    .MixedReality
    -0.06
    POSITIVE LOGITS
    frau
    0.07
     стан
    0.06
    	person
    0.06
     アル
    0.06
    él
    0.06
     SCE
    0.06
     cheque
    0.06
     дома
    0.06
     tạm
    0.06
    otonin
    0.06
    Activations Density 0.045%

    No Known Activations