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. 11-RESID-POST-AA
    6. 8269
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the word “decision.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isode
    -0.06
    idae
    -0.06
    �
    -0.06
     larg
    -0.06
    інг
    -0.06
     ]}↵
    -0.06
    }$/
    -0.06
     ký
    -0.06
    (Player
    -0.06
    .CommandText
    -0.06
    POSITIVE LOGITS
    EOS
    0.07
     çiz
    0.06
    $menu
    0.06
    下载次数
    0.06
     독일
    0.06
    开放
    0.06
    Contrib
    0.06
     Cann
    0.06
     //{↵
    0.06
     captions
    0.06
    Activations Density 0.000%

    No Known Activations