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. 16-LLAMASCOPE-RES-32K
    6. 21774
    Prev
    Next
    INDEX
    Explanations

    references to food-related events and their settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /downloads
    -0.15
    allen
    -0.15
     Rei
    -0.14
     TextAlign
    -0.14
    ¶Į
    -0.13
    à¹īาห
    -0.13
    íıī
    -0.13
    ierge
    -0.12
    endid
    -0.12
    /generated
    -0.12
    POSITIVE LOGITS
     actual
    0.48
     full
    0.47
    actual
    0.40
    full
    0.38
     Actual
    0.37
    /full
    0.35
    (full
    0.34
     FULL
    0.33
    (actual
    0.33
    Actual
    0.33
    Activations Density 0.314%

    No Known Activations