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. 27-LLAMASCOPE-RES-32K
    6. 1661
    Prev
    Next
    INDEX
    Explanations

    references to international conferences and seminars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    íĨµ
    -0.14
    æŃ²
    -0.14
     Episodes
    -0.14
    geme
    -0.14
    è
    -0.14
    ÙĪÙĨد
    -0.13
    ÙĬرا
    -0.13
    cheid
    -0.13
    æŃ³
    -0.13
     Committees
    -0.13
    POSITIVE LOGITS
     conference
    0.65
     Conference
    0.53
    conference
    0.52
     sym
    0.50
    Conference
    0.47
     conferences
    0.46
     конÑĦеÑĢен
    0.43
     summit
    0.42
     confer
    0.40
     forum
    0.39
    Activations Density 0.289%

    No Known Activations