© 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. 27-LLAMASCOPE-RES-32K
    11. 10278
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptors that emphasize the frequency or abundance of elements or concerns in the text

    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
     most
    -0.18
    358
    -0.14
    ibe
    -0.14
    ãĤĪãģı
    -0.14
     æľĢ
    -0.13
    æľĢ
    -0.13
     penchant
    -0.13
    -0.13
     anything
    -0.13
     eines
    -0.13
    POSITIVE LOGITS
     ways
    0.44
     Ways
    0.32
     reasons
    0.31
    ways
    0.28
    reason
    0.27
     places
    0.25
     reason
    0.25
     Reasons
    0.23
    Reason
    0.23
     occasions
    0.22
    Activations Density 0.123%

    No Known Activations