© 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 (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 105117
    Prev
    Next
    INDEX
    Explanations

    some

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seeded
    -0.07
     دقیقه
    -0.06
     yapılması
    -0.06
    Endpoints
    -0.06
     đôi
    -0.06
    Про
    -0.06
     pathways
    -0.06
    ilmiştir
    -0.06
     hallmark
    -0.06
    αι
    -0.06
    POSITIVE LOGITS
     mortal
    0.07
    -general
    0.06
     greeting
    0.06
     fights
    0.06
    FINITY
    0.06
     offended
    0.06
     enraged
    0.06
     Freder
    0.06
    OutOfBoundsException
    0.06
    _recursive
    0.06
    Activations Density 0.022%

    No Known Activations