© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 4-LLAMASCOPE-RES-32K
    11. 2163
    Prev
    Next
    INDEX
    Explanations

    references to video game characters and elements, particularly in relation to the Final Fantasy series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    боÑĤ
    -0.17
    ilk
    -0.15
    amma
    -0.15
    /sn
    -0.15
    oud
    -0.15
    dle
    -0.14
    ilik
    -0.14
    opus
    -0.14
    uchs
    -0.14
     Sn
    -0.13
    POSITIVE LOGITS
    leep
    0.16
    ãĥªãĤ¢
    0.16
    ACITY
    0.15
     useClass
    0.15
    lico
    0.15
    Animations
    0.15
    _via
    0.15
    ONA
    0.15
    gv
    0.15
    ogo
    0.14
    Activations Density 0.190%

    No Known Activations