Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 93157
    Prev
    Next
    INDEX
    Explanations

    service

    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
    uggy
    -0.08
    _para
    -0.06
     Reality
    -0.06
    ilmektedir
    -0.06
    Wat
    -0.06
     steril
    -0.06
     Sản
    -0.06
    @Service
    -0.06
     Pad
    -0.06
    _/
    -0.06
    POSITIVE LOGITS
    _doc
    0.07
     brutality
    0.07
     militant
    0.07
     रखत
    0.06
    closing
    0.06
    opens
    0.06
     eh
    0.06
    async
    0.06
    OPTION
    0.06
    	echo
    0.06
    Activations Density 0.008%

    No Known Activations