Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 21807
    Prev
    Next
    INDEX
    Explanations

    phrases related to the specifications and capabilities of a machine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Transfer
    -0.16
    .transfer
    -0.16
    transfer
    -0.15
    _DEAD
    -0.15
    Round
    -0.14
     bund
    -0.14
    ayne
    -0.14
    á»ijc
    -0.14
    Transfer
    -0.14
    alg
    -0.14
    POSITIVE LOGITS
     fold
    0.29
     folding
    0.28
    -fold
    0.27
     Fold
    0.25
     Folding
    0.24
     unfolding
    0.23
     unfolded
    0.23
    Fold
    0.22
     folds
    0.21
    fold
    0.21
    Activations Density 0.220%

    No Known Activations