Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 1721
    Prev
    Next
    INDEX
    Explanations

    negation and expressions that counter claims or expectations

    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
    ybrid
    -0.17
     neither
    -0.16
    à¸ĸ
    -0.16
    lef
    -0.16
     hardly
    -0.15
    ä¸įäºĨ
    -0.15
     no
    -0.15
    eve
    -0.15
     Almost
    -0.15
    affle
    -0.15
    POSITIVE LOGITS
     altogether
    0.24
     stint
    0.22
    alto
    0.19
     mere
    0.17
     greatly
    0.17
     Alto
    0.15
     merely
    0.15
     seriously
    0.15
     strictly
    0.15
    Overall
    0.15
    Activations Density 0.577%

    No Known Activations