© 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. 23-LLAMASCOPE-RES-32K
    11. 1005
    Prev
    Next
    INDEX
    Explanations

    key nouns and phrases referencing significant events or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yüzden
    -0.15
    Å¡ti
    -0.14
    zin
    -0.14
     ãĢ
    -0.13
    æī¾
    -0.13
    ult
    -0.13
    جÙĦ
    -0.12
    _FIND
    -0.12
    ð
    -0.12
    vyk
    -0.12
    POSITIVE LOGITS
     another
    0.63
    another
    0.54
     Another
    0.45
    Another
    0.44
    åı¦ä¸Ģ
    0.39
    åı¦
    0.35
     otra
    0.34
     otro
    0.32
     ëĺIJ
    0.31
    åı¦å¤ĸ
    0.29
    Activations Density 0.023%

    No Known Activations