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. 24-LLAMASCOPE-RES-32K
    6. 14680
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to strategies and decision-making in business contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itle
    -0.13
    bih
    -0.13
    itel
    -0.13
    æ½
    -0.13
     Technologies
    -0.13
    Ậ
    -0.13
     caveat
    -0.13
    ICO
    -0.13
    TeV
    -0.13
    è§Ħå®ļ
    -0.13
    POSITIVE LOGITS
     strategy
    0.86
    strategy
    0.77
     Strategy
    0.77
     strategies
    0.69
    Strategy
    0.69
    _strategy
    0.64
     strateg
    0.60
    çŃĸ
    0.59
     Strategies
    0.59
    .strategy
    0.58
    Activations Density 0.199%

    No Known Activations