© 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. 30-LLAMASCOPE-RES-32K
    11. 18264
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific topics and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Science
    -0.24
    Science
    -0.23
    science
    -0.23
     science
    -0.21
     scientifically
    -0.20
    ted
    -0.18
     Sciences
    -0.18
    haar
    -0.17
    ç§ijåѦ
    -0.17
     sciences
    -0.16
    POSITIVE LOGITS
    ally
    0.36
    /engine
    0.33
    /math
    0.27
    ALLY
    0.25
    -fiction
    0.20
    /art
    0.18
    emet
    0.18
     journal
    0.18
     discovery
    0.18
    /re
    0.18
    Activations Density 0.056%

    No Known Activations