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. 25-LLAMASCOPE-RES-32K
    6. 22859
    Prev
    Next
    INDEX
    Explanations

    references to geological and marine science concepts, particularly related to gas hydrates and sediment properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     underground
    -0.16
     Jane
    -0.16
     pitch
    -0.14
    apus
    -0.14
     Kunst
    -0.14
     Underground
    -0.13
    æ¼
    -0.13
     Pier
    -0.13
    otive
    -0.13
     decom
    -0.13
    POSITIVE LOGITS
     Sed
    0.31
     sed
    0.31
     sediment
    0.30
     depos
    0.28
     eros
    0.25
    SED
    0.22
    sed
    0.22
    olian
    0.21
     scour
    0.21
     er
    0.21
    Activations Density 0.057%

    No Known Activations