© 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. 10932
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrasting or conditional relationships

    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
     itself
    -0.16
     nữa
    -0.14
     notamment
    -0.14
    iyim
    -0.14
     ÑģебÑı
    -0.14
     então
    -0.14
     quindi
    -0.14
     yani
    -0.14
    izzling
    -0.13
     otherwise
    -0.13
    POSITIVE LOGITS
     although
    0.45
     while
    0.42
     whereas
    0.37
     despite
    0.37
     unlike
    0.36
    although
    0.34
     since
    0.33
    while
    0.33
     when
    0.30
     unless
    0.30
    Activations Density 0.930%

    No Known Activations