© 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. 17783
    Prev
    Next
    INDEX
    Explanations

    terms related to nanotechnology and its applications

    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
    \Queue
    -0.16
    _vk
    -0.15
    _AHB
    -0.14
    lun
    -0.14
    guess
    -0.14
    .atan
    -0.14
    lesia
    -0.14
    _recovery
    -0.14
    auen
    -0.13
    xa
    -0.13
    POSITIVE LOGITS
    -scale
    0.29
    structures
    0.28
     scale
    0.28
    structured
    0.28
    ometer
    0.27
    otechnology
    0.26
    -sized
    0.26
    scale
    0.26
     Scale
    0.25
    particles
    0.25
    Activations Density 0.007%

    No Known Activations