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. 18-LLAMASCOPE-RES-32K
    6. 5850
    Prev
    Next
    INDEX
    Explanations

    references to conferences and events related to professional gatherings or discussions

    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
    zier
    -0.15
    .rc
    -0.14
    bjerg
    -0.13
     Král
    -0.13
    atron
    -0.13
    otate
    -0.13
    ellan
    -0.13
    اÙĪØ±
    -0.13
    imulator
    -0.12
    anky
    -0.12
    POSITIVE LOGITS
     called
    0.97
    called
    0.84
     Called
    0.76
    Called
    0.68
     titled
    0.68
    åı«
    0.66
     named
    0.66
     entitled
    0.61
    -called
    0.60
     llam
    0.57
    Activations Density 0.557%

    No Known Activations