© 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. 27-LLAMASCOPE-RES-32K
    11. 2657
    Prev
    Next
    INDEX
    Explanations

    content related to detailed procedural descriptions and scientific data analysis

    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
    znik
    -0.17
    (strict
    -0.16
    /slick
    -0.16
    缼
    -0.16
    inks
    -0.16
    Sink
    -0.16
    SX
    -0.15
     Seah
    -0.15
     sinks
    -0.15
    oux
    -0.15
    POSITIVE LOGITS
     sample
    0.91
     samples
    0.88
     Sample
    0.79
    sample
    0.79
     Samples
    0.77
    -sample
    0.73
    _sample
    0.73
    Sample
    0.73
    samples
    0.72
     SAMPLE
    0.71
    Activations Density 0.110%

    No Known Activations