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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11942
    Prev
    Next
    INDEX
    Explanations

    references to specific months and seasonal events

    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
     Easter
    -0.41
    June
    -0.35
     spring
    -0.34
    April
    -0.33
     Spring
    -0.32
    æĺ¥
    -0.31
    Spring
    -0.31
     June
    -0.30
    March
    -0.30
     APR
    -0.29
    POSITIVE LOGITS
     Oct
    0.85
     oct
    0.82
    Oct
    0.81
     October
    0.79
    October
    0.79
    oct
    0.77
    /oct
    0.73
    _oct
    0.72
     Halloween
    0.70
     OCT
    0.69
    Activations Density 0.277%

    No Known Activations