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. 3-RESID-POST-AA
    6. 122832
    Prev
    Next
    INDEX
    Explanations

    html tags

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    110
    -0.07
    .lp
    -0.07
     또한
    -0.07
    :",
    -0.07
    	ui
    -0.07
    :["
    -0.07
    ','');↵
    -0.07
    670
    -0.07
    】
    -0.07
    }}">↵
    -0.07
    POSITIVE LOGITS
    pheric
    0.07
    Stone
    0.07
    _literal
    0.06
    bral
    0.06
     František
    0.06
     Mohamed
    0.06
     الإسلام
    0.05
    Gro
    0.05
     présent
    0.05
     기다
    0.05
    Activations Density 0.040%

    No Known Activations