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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 6071
    Prev
    Next
    INDEX
    Explanations

    references to nationality, identity, and citizenship concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -0.19
     Ø®ÙĪØ¯Ø´
    -0.18
    izedName
    -0.15
    rik
    -0.14
    ira
    -0.14
     Böyle
    -0.14
    olit
    -0.14
    367
    -0.14
     hoá
    -0.14
    uan
    -0.14
    POSITIVE LOGITS
     respectively
    0.33
     respective
    0.29
     themselves
    0.18
     their
    0.18
    witter
    0.17
    åĪĨåĪ«
    0.17
    their
    0.17
    Their
    0.16
     ê°ģê°ģ
    0.16
     alike
    0.15
    Activations Density 0.930%

    No Known Activations