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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-LLAMASCOPE-RES-32K
    6. 8476
    Prev
    Next
    INDEX
    Explanations

    concepts related to immediate satisfaction versus long-term planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eventually
    -0.19
     nakonec
    -0.17
     Eventually
    -0.17
    uzzi
    -0.16
     eventual
    -0.16
    declspec
    -0.15
    reira
    -0.15
    Eventually
    -0.15
    ohan
    -0.15
    andalone
    -0.15
    POSITIVE LOGITS
     immediate
    0.67
     immediately
    0.65
     immedi
    0.58
     Immediate
    0.51
     Immediately
    0.47
     sofort
    0.47
     instantly
    0.44
    Immediate
    0.41
    ç«ĭåĪ»
    0.37
    Immediately
    0.36
    Activations Density 0.074%

    No Known Activations