© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 21-LLAMASCOPE-RES-32K
    11. 14950
    Prev
    Next
    INDEX
    Explanations

    phrases indicating connections or relationships between concepts or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     some
    -0.20
     Some
    -0.20
    some
    -0.20
     SOME
    -0.20
    ä¸ĢäºĽ
    -0.18
    Some
    -0.17
    äºĽ
    -0.17
    "Some
    -0.16
    zos
    -0.16
    .some
    -0.16
    POSITIVE LOGITS
     another
    0.63
    another
    0.55
     Another
    0.53
    Another
    0.49
    åı¦
    0.44
    åı¦ä¸Ģ
    0.38
     otra
    0.37
     otro
    0.37
     others
    0.33
     outra
    0.32
    Activations Density 0.044%

    No Known Activations