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. 20-LLAMASCOPE-RES-32K
    6. 23820
    Prev
    Next
    INDEX
    Explanations

    aspirations and future possibilities conveyed through phrases about "one day."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hemen
    -0.18
     Immediate
    -0.17
    Immediate
    -0.16
     instantly
    -0.16
    nea
    -0.15
     immediate
    -0.15
    ìłĿ
    -0.15
    _losses
    -0.15
    dorf
    -0.15
     immediately
    -0.15
    POSITIVE LOGITS
     someday
    0.70
     eventually
    0.67
     eventual
    0.63
     Eventually
    0.58
    Eventually
    0.56
    eday
    0.44
     sooner
    0.43
     future
    0.41
     ultimately
    0.37
    future
    0.34
    Activations Density 0.356%

    No Known Activations