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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 80617
    Prev
    Next
    INDEX
    Explanations

    ai

    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
     subtotal
    -0.07
     imposing
    -0.07
     talk
    -0.06
    \Block
    -0.06
    rypt
    -0.06
    hores
    -0.06
    ッシュ
    -0.06
     Tooth
    -0.06
    RowCount
    -0.06
     managing
    -0.05
    POSITIVE LOGITS
     ğ
    0.06
    DV
    0.06
    ("'",
    0.06
     statistically
    0.06
    	 		
    0.06
    ypo
    0.06
    nv
    0.06
    店
    0.06
     indis
    0.06
     bì
    0.06
    Activations Density 0.002%

    No Known Activations