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. 23-RESID-POST-AA
    6. 103831
    Prev
    Next
    INDEX
    Explanations

    E

    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
     nga
    -0.07
     walking
    -0.07
     nằm
    -0.07
    imulation
    -0.06
    ́c
    -0.06
     rewarded
    -0.06
     tempo
    -0.06
     novembre
    -0.06
     importante
    -0.06
     Minds
    -0.06
    POSITIVE LOGITS
    演
    0.07
    (compact
    0.07
    Fourth
    0.06
     socio
    0.06
     NoSuch
    0.06
     kadınlar
    0.06
    izyon
    0.06
    责
    0.06
    _define
    0.06
    \Product
    0.06
    Activations Density 0.012%

    No Known Activations