© 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. 1553
    Prev
    Next
    INDEX
    Explanations

    elements related to organization, structure, and operational efficiency

    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
    ìĿ´ê³ł
    -0.24
     ìŀĪê³ł
    -0.22
    )&&
    -0.21
    	and
    -0.21
    '&&
    -0.19
    ä¸Ķ
    -0.19
    并
    -0.18
    ì§Ģê³ł
    -0.18
    ãģ§ãģĤãĤĬ
    -0.18
    )&&(
    -0.18
    POSITIVE LOGITS
     alike
    0.36
     respectively
    0.31
    —all
    0.25
     etc
    0.23
     Äijá»ģu
    0.23
    etc
    0.22
    çŃī
    0.22
     all
    0.22
     thereof
    0.21
    -all
    0.21
    Activations Density 0.999%

    No Known Activations