© 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. 7-RESID-POST-AA
    11. 71655
    Prev
    Next
    INDEX
    Explanations

    </

    np_max-act · gemini-2.0-flash
    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
     část
    -0.07
     pity
    -0.06
     کیفیت
    -0.06
    éra
    -0.06
    ernet
    -0.06
     eat
    -0.06
    halten
    -0.06
    Amazon
    -0.06
    Increasing
    -0.06
    _repo
    -0.06
    POSITIVE LOGITS
     Sup
    0.06
    	bg
    0.06
    		↵↵
    0.06
     '';↵
    0.06
     rested
    0.06
     slime
    0.06
     Bless
    0.06
     Fah
    0.06
     Uses
    0.06
    unda
    0.06
    Activations Density 0.010%

    No Known Activations