© 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. 11933
    Prev
    Next
    INDEX
    Explanations

    references to experimental results and performance metrics in a technical context

    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
    Draft
    -0.15
    iol
    -0.15
    ijkstra
    -0.14
     Draft
    -0.14
     Investments
    -0.13
    fal
    -0.13
    umble
    -0.13
    hips
    -0.13
    lage
    -0.13
    íĪ¬
    -0.13
    POSITIVE LOGITS
     dataset
    0.33
    dataset
    0.30
     Dataset
    0.28
    benchmark
    0.28
    Dataset
    0.28
     benchmark
    0.26
     datasets
    0.26
    _dataset
    0.26
    .dataset
    0.24
    nist
    0.23
    Activations Density 0.076%

    No Known Activations