© 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. 27-LLAMASCOPE-RES-32K
    11. 12678
    Prev
    Next
    INDEX
    Explanations

    references to competitions and awards related to creativity or artistic endeavors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    robat
    -0.14
    ÎŃαÏĤ
    -0.14
    _ASSUME
    -0.14
    ìĪł
    -0.14
     Bilim
    -0.13
    ikel
    -0.13
    á»ijt
    -0.13
    ebo
    -0.13
    ê¸ī
    -0.13
    ogy
    -0.13
    POSITIVE LOGITS
     entries
    0.52
     judges
    0.51
     competition
    0.50
     submissions
    0.47
     Entries
    0.46
     contest
    0.45
     Judges
    0.45
    Entries
    0.44
    entries
    0.44
     judging
    0.44
    Activations Density 0.397%

    No Known Activations