© 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. 28686
    Prev
    Next
    INDEX
    Explanations

    inquiries about pronunciation, particularly of Swedish and related languages

    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
     Arthropoda
    -0.14
     Direct
    -0.14
    lat
    -0.14
    iyat
    -0.14
    icolor
    -0.14
    erin
    -0.13
     spatial
    -0.13
    .yy
    -0.13
    indows
    -0.13
    agues
    -0.13
    POSITIVE LOGITS
     glide
    0.19
     vowel
    0.19
     nasal
    0.18
     sounds
    0.18
     IPA
    0.17
    éŁ³
    0.17
    лиз
    0.16
    èĪĮ
    0.16
     sound
    0.16
     Glide
    0.15
    Activations Density 0.039%

    No Known Activations