© 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. 24-LLAMASCOPE-RES-32K
    11. 6486
    Prev
    Next
    INDEX
    Explanations

    references to telecommunications and communication technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mey
    -0.16
    олом
    -0.15
    lify
    -0.15
    MPI
    -0.14
     zim
    -0.14
    DOMNode
    -0.14
     insider
    -0.14
    teki
    -0.14
     tek
    -0.14
    ancode
    -0.14
    POSITIVE LOGITS
     satellites
    0.24
     constellation
    0.22
     satellite
    0.21
    sat
    0.21
    coverage
    0.20
     Coverage
    0.19
     Alphabet
    0.19
     const
    0.19
    Coverage
    0.18
    const
    0.18
    Activations Density 0.003%

    No Known Activations