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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-LLAMASCOPE-RES-32K
    6. 2657
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of automotive systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vod
    -0.17
    antha
    -0.16
    draul
    -0.16
    ogan
    -0.15
    .getRaw
    -0.14
    xin
    -0.14
    fullscreen
    -0.14
    agn
    -0.14
    _fixture
    -0.14
    Outcome
    -0.13
    POSITIVE LOGITS
     rear
    0.21
     Rear
    0.17
    chein
    0.16
    rear
    0.15
     front
    0.15
    eric
    0.14
     dealer
    0.14
    Front
    0.14
     Pir
    0.13
    -inc
    0.13
    Activations Density 0.010%

    No Known Activations