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. 23-LLAMASCOPE-RES-32K
    6. 593
    Prev
    Next
    INDEX
    Explanations

    seasonal themes and references to spring activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     August
    -0.35
     September
    -0.34
    September
    -0.33
    August
    -0.33
    October
    -0.32
     oct
    -0.32
     Halloween
    -0.32
    /oct
    -0.32
     October
    -0.32
     November
    -0.29
    POSITIVE LOGITS
    April
    0.76
     spring
    0.74
     April
    0.73
     Easter
    0.71
     Spring
    0.70
     March
    0.69
    March
    0.68
    -Apr
    0.66
    spring
    0.64
    Apr
    0.63
    Activations Density 0.593%

    No Known Activations