© 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. 8559
    Prev
    Next
    INDEX
    Explanations

    references to supplemental materials and auxiliary aids in documents

    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
    isoft
    -0.17
    ucc
    -0.15
    หลวà¸ĩ
    -0.14
    asher
    -0.14
    ìĨ¡
    -0.14
    oken
    -0.14
     Mey
    -0.14
    Specifier
    -0.13
     undef
    -0.13
    ÙĨÙĩ
    -0.13
    POSITIVE LOGITS
    endum
    0.21
    /sub
    0.19
    /helper
    0.19
    /add
    0.19
    iliary
    0.18
    illary
    0.18
    arily
    0.16
    airy
    0.16
    ILI
    0.16
    olar
    0.16
    Activations Density 0.085%

    No Known Activations