© 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. 10-LLAMASCOPE-RES-32K
    11. 29837
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºī
    -0.14
    inder
    -0.14
    iv
    -0.13
    ounter
    -0.13
     pes
    -0.13
     terms
    -0.13
    ä½į
    -0.13
    onth
    -0.13
    ibal
    -0.13
     puls
    -0.13
    POSITIVE LOGITS
    uien
    0.16
    insn
    0.14
     embargo
    0.14
    rig
    0.14
    yan
    0.14
    ':''
    0.13
     è¦
    0.13
    æĭ³
    0.13
     Pist
    0.13
    .runner
    0.13
    Activations Density 0.083%

    No Known Activations