© 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. 2425
    Prev
    Next
    INDEX
    Explanations

    references to historical and cultural elements in cinema

    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
    was
    -0.30
    Was
    -0.25
     wasn
    -0.25
     isn
    -0.24
     was
    -0.24
     Was
    -0.24
     is
    -0.23
    _was
    -0.22
     ÑģÑĤанеÑĤ
    -0.21
     isnt
    -0.19
    POSITIVE LOGITS
     are
    0.70
     were
    0.68
     weren
    0.55
     são
    0.55
     Were
    0.54
     sont
    0.53
     aren
    0.52
    were
    0.52
     waren
    0.52
     jsou
    0.50
    Activations Density 0.106%

    No Known Activations