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. 3-RESID-POST-AA
    6. 122197
    Prev
    Next
    INDEX
    Explanations

    senescence

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hopping
    -0.07
    .aspx
    -0.07
     reefs
    -0.07
    巻
    -0.06
    前の
    -0.06
    ým
    -0.06
    IDD
    -0.06
    _perms
    -0.06
    اث
    -0.06
     dome
    -0.06
    POSITIVE LOGITS
     sen
    0.17
    spor
    0.14
    .reflect
    0.09
     TObject
    0.07
    онт
    0.07
     Sen
    0.07
    	internal
    0.06
    .Restr
    0.06
     spor
    0.06
    	continue
    0.06
    Activations Density 0.002%

    No Known Activations