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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 27-RESID-POST-AA
    6. 73434
    Prev
    Next
    INDEX
    Explanations

    Linux file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    كام
    -0.07
    esi
    -0.06
     شیر
    -0.06
    usters
    -0.06
    igslist
    -0.06
    maktan
    -0.06
     국민
    -0.06
    電子
    -0.06
    ;;;
    -0.06
     stereotype
    -0.06
    POSITIVE LOGITS
     favour
    0.06
    ως
    0.06
     Bell
    0.06
     Salmon
    0.06
     summers
    0.06
    	Service
    0.06
    塚
    0.06
     useRouter
    0.06
    'Neill
    0.06
     ώ
    0.06
    Activations Density 0.004%

    No Known Activations