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

    Neuronpedia

    Jacobian LensNEW
    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. 3702
    Prev
    Next
    INDEX
    Explanations

    corrections and references to attribution changes in text

    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
     unsuccessful
    -0.15
    reh
    -0.15
     predict
    -0.14
     mediocre
    -0.13
     anonymously
    -0.13
     hardly
    -0.13
     indirectly
    -0.13
     mock
    -0.13
     cons
    -0.13
    hausen
    -0.13
    POSITIVE LOGITS
     correct
    0.41
     incorrect
    0.40
     mistake
    0.39
     error
    0.39
    éĶĻ误
    0.35
     errors
    0.35
    incorrect
    0.34
     mistakes
    0.34
    æŃ£ç¡®
    0.33
    誤
    0.33
    Activations Density 0.451%

    No Known Activations