© 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. 1519
    Prev
    Next
    INDEX
    Explanations

    elements related to policy decisions and their impact on society

    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
    once
    -0.13
    ειο
    -0.13
    ãĥ
    -0.12
    GORITH
    -0.12
    ÚĺÙĩ
    -0.12
    аÑĪа
    -0.11
     geil
    -0.11
    emoc
    -0.10
    Å¡tÃŃ
    -0.10
    ÑĸллÑı
    -0.10
    POSITIVE LOGITS
     on
    1.19
     trên
    0.77
     на
    0.77
     auf
    0.72
     عÙĦÙī
    0.71
     på
    0.66
    	on
    0.63
     pada
    0.59
    à¸ļà¸Ļ
    0.54
    _on
    0.53
    Activations Density 3.613%

    No Known Activations