© 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. 31-LLAMASCOPE-RES-32K
    11. 1794
    Prev
    Next
    INDEX
    Explanations

    key concepts and terms associated with technology and digital mediums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -License
    -0.17
    -pills
    -0.17
    -msg
    -0.17
    -One
    -0.17
    -svg
    -0.17
    -upper
    -0.17
    -{
    -0.17
    -The
    -0.17
    -With
    -0.17
    -'
    -0.17
    POSITIVE LOGITS
    -driven
    0.55
    -oriented
    0.48
    -based
    0.48
    -focused
    0.47
    -friendly
    0.47
    -filled
    0.46
    -dominated
    0.46
    -backed
    0.46
    -packed
    0.45
    -rich
    0.45
    Activations Density 0.862%

    No Known Activations