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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 80729
    Prev
    Next
    INDEX
    Explanations

    travel directions/locations

    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
    ISK
    -0.07
    .UI
    -0.06
     />,↵
    -0.06
     thugs
    -0.06
    axis
    -0.06
    horn
    -0.06
    olah
    -0.06
     ammo
    -0.06
    cairo
    -0.06
    Larry
    -0.06
    POSITIVE LOGITS
    ]:=
    0.06
     Wall
    0.06
    =!
    0.06
     нар
    0.06
    oseconds
    0.06
    ]=
    0.06
    /templates
    0.06
    BeforeEach
    0.06
    )x
    0.06
    			    
    0.06
    Activations Density 0.021%

    No Known Activations