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. 11-RESID-POST-AA
    6. 101276
    Prev
    Next
    INDEX
    Explanations

    Technical/Academic subjects

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StObject
    -0.07
     revolving
    -0.07
    ordo
    -0.07
     Centro
    -0.07
    tech
    -0.07
     setIs
    -0.06
     Vườn
    -0.06
    wiąz
    -0.06
     neuro
    -0.06
     magg
    -0.06
    POSITIVE LOGITS
     Until
    0.06
    овал
    0.06
     Flexible
    0.06
     Tools
    0.06
    Contained
    0.06
     battles
    0.06
     compressed
    0.06
     heightened
    0.06
     collision
    0.05
     Sadly
    0.05
    Activations Density 0.576%

    No Known Activations