© 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. 20-LLAMASCOPE-RES-32K
    11. 13484
    Prev
    Next
    INDEX
    Explanations

    key event details and descriptions related to conferences or exhibitions

    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
     month
    -0.24
     Month
    -0.23
     Monthly
    -0.23
     summer
    -0.23
     monthly
    -0.22
    -month
    -0.21
     Weeks
    -0.21
     months
    -0.21
    Monthly
    -0.21
    /month
    -0.20
    POSITIVE LOGITS
     Saturday
    0.40
     Friday
    0.40
     Thursday
    0.37
     Sunday
    0.34
     day
    0.32
     Day
    0.32
    Saturday
    0.32
    Friday
    0.31
     friday
    0.31
    Thursday
    0.31
    Activations Density 0.205%

    No Known Activations