© 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. 16-LLAMASCOPE-RES-32K
    11. 22360
    Prev
    Next
    INDEX
    Explanations

    terms related to products, particularly those used in health and wellness contexts

    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
     bottom
    -0.15
     itemprop
    -0.15
     principal
    -0.15
    enheim
    -0.15
     Luz
    -0.14
    ëŀĢ
    -0.14
     Fil
    -0.14
     sheet
    -0.14
    ea
    -0.14
     Principal
    -0.14
    POSITIVE LOGITS
     version
    0.40
    version
    0.37
     versions
    0.35
     VERSION
    0.33
    -version
    0.32
    çīĪæľ¬
    0.29
     Version
    0.29
    versions
    0.28
    _version
    0.28
    Version
    0.28
    Activations Density 0.333%

    No Known Activations