© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 20245
    Prev
    Next
    INDEX
    Explanations

    elements related to influence and achievements in aviation writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ramos
    -0.19
    rough
    -0.18
    runner
    -0.17
    .infinity
    -0.17
    rael
    -0.17
    rod
    -0.15
    repos
    -0.15
    relay
    -0.15
    ACITY
    -0.15
     reels
    -0.15
    POSITIVE LOGITS
     Richard
    1.19
    Richard
    1.12
     Richardson
    0.90
     Richards
    0.88
     rich
    0.67
     richness
    0.66
    rich
    0.65
     Richmond
    0.61
     Rich
    0.59
    Rich
    0.59
    Activations Density 0.047%

    No Known Activations