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. 8-LLAMASCOPE-RES-32K
    6. 22721
    Prev
    Next
    INDEX
    Explanations

    terms related to neutron stars and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ethe
    -0.17
    æı®
    -0.16
    rzy
    -0.15
    onen
    -0.15
     triple
    -0.15
    iesta
    -0.14
    eced
    -0.14
    親
    -0.14
    Cerrar
    -0.14
    athers
    -0.14
    POSITIVE LOGITS
    ÏĥÏĥ
    0.16
    indow
    0.15
    åİ
    0.15
     McD
    0.15
    att
    0.14
    swire
    0.14
    packing
    0.14
    ALA
    0.14
    .tab
    0.14
     Mis
    0.14
    Activations Density 0.012%

    No Known Activations