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. 15-RESID-POST-AA
    6. 41523
    Prev
    Next
    INDEX
    Explanations

    Words ending with "or"

    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
     ken
    -0.08
     mě
    -0.07
    ์แ
    -0.07
    ые
    -0.07
    一个人
    -0.07
     �
    -0.07
    ane
    -0.07
     Anne
    -0.07
    ��
    -0.07
    ンデ
    -0.07
    POSITIVE LOGITS
    ator
    0.09
    or
    0.09
    ktor
    0.08
    ATOR
    0.08
    Detector
    0.08
    Factor
    0.08
    mentor
    0.08
    ITOR
    0.08
    cir
    0.08
     Raptors
    0.07
    Activations Density 0.079%

    No Known Activations