© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 73323
    Prev
    Next
    INDEX
    Explanations

    loser failure

    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
    Construction
    -0.07
    句话
    -0.06
     caves
    -0.06
    unbind
    -0.06
    /drivers
    -0.06
     Yard
    -0.06
    ])),↵
    -0.06
    iasi
    -0.05
     batches
    -0.05
    	menu
    -0.05
    POSITIVE LOGITS
     PIT
    0.06
    oon
    0.06
     {\
    0.06
    .IsNull
    0.06
     collectively
    0.06
    ads
    0.06
    th
    0.06
    kg
    0.06
     来
    0.06
     �
    0.06
    Activations Density 0.021%

    No Known Activations