© 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. 16-LLAMASCOPE-RES-32K
    11. 6383
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruba
    -0.16
    egl
    -0.15
    wish
    -0.15
     wishes
    -0.15
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.14
    Ñģон
    -0.14
    ritch
    -0.14
    .schema
    -0.14
     gó
    -0.13
     Wish
    -0.13
    POSITIVE LOGITS
    izza
    0.19
    oppel
    0.15
    azole
    0.15
    ojis
    0.14
     Radius
    0.14
    ÏĢο
    0.14
    ores
    0.14
    ÑįÑĦ
    0.13
     honour
    0.13
    üme
    0.13
    Activations Density 0.023%

    No Known Activations