© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 1920
    Prev
    Next
    INDEX
    Explanations

    financial and legal terminology related to costs and liabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strup
    -0.16
     SEQ
    -0.15
    ãĢ
    -0.14
     Cbd
    -0.14
     Southeast
    -0.14
    ynes
    -0.14
     Seq
    -0.14
     Werner
    -0.14
    enses
    -0.14
     Ea
    -0.14
    POSITIVE LOGITS
     also
    0.17
     ALSO
    0.15
    also
    0.15
    -ignore
    0.14
     Pist
    0.14
     Obl
    0.14
     Pett
    0.14
     Pistol
    0.14
     blog
    0.14
     Petroleum
    0.13
    Activations Density 0.017%

    No Known Activations