© 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. 21650
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific measurements and analysis

    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
    uala
    -0.16
     赤
    -0.15
    èĭ
    -0.15
     traps
    -0.15
    dou
    -0.14
    nad
    -0.14
     dai
    -0.14
     balloons
    -0.14
    ione
    -0.14
    ouv
    -0.14
    POSITIVE LOGITS
     dif
    0.23
     diff
    0.23
     syn
    0.23
     beam
    0.22
     Beam
    0.21
    dif
    0.19
    beam
    0.19
    Beam
    0.18
     Patterson
    0.17
     powder
    0.17
    Activations Density 0.007%

    No Known Activations