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. 2641
    Prev
    Next
    INDEX
    Explanations

    references to time-related concepts

    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
     return
    -0.29
     Return
    -0.26
     returning
    -0.26
     returns
    -0.25
     RETURN
    -0.24
    (return
    -0.24
    return
    -0.24
    (Return
    -0.23
     Returns
    -0.23
     returned
    -0.22
    POSITIVE LOGITS
     backed
    0.49
    -backed
    0.44
     backing
    0.43
     backs
    0.42
    Backing
    0.39
    bach
    0.35
    -back
    0.35
    backs
    0.34
    bac
    0.32
     bach
    0.31
    Activations Density 0.147%

    No Known Activations