© 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. 21271
    Prev
    Next
    INDEX
    Explanations

    phrases indicating finality or last occurrences

    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
    rtle
    -0.16
    ickle
    -0.15
     COPYING
    -0.15
    romo
    -0.15
    oningen
    -0.15
    ffa
    -0.14
    reet
    -0.14
    ckpt
    -0.14
    ifa
    -0.14
    .transport
    -0.14
    POSITIVE LOGITS
     final
    0.83
    final
    0.67
     last
    0.66
    æľĢåIJİ
    0.62
     Final
    0.60
     FINAL
    0.59
    æľĢå¾Į
    0.59
    -final
    0.57
     ë§Īì§Ģë§ī
    0.55
    Final
    0.54
    Activations Density 0.242%

    No Known Activations