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. 15-RESID-POST-AA
    6. 10925
    Prev
    Next
    INDEX
    Explanations

    seal

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	time
    -0.07
    ittance
    -0.07
    ixture
    -0.07
    っち
    -0.06
     Subjects
    -0.06
    big
    -0.06
     Opport
    -0.06
    itudes
    -0.06
    	act
    -0.06
     burger
    -0.06
    POSITIVE LOGITS
     sealed
    0.11
     sealing
    0.10
     Seal
    0.08
     seal
    0.08
     SEAL
    0.07
    sealed
    0.07
     clarity
    0.07
    SENS
    0.07
     lethal
    0.07
    ่อง
    0.07
    Activations Density 0.007%

    No Known Activations