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. 21-LLAMASCOPE-RES-32K
    6. 10502
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mathematical modeling and simulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azo
    -0.17
     Tune
    -0.16
    .gg
    -0.15
    Looper
    -0.15
    ieee
    -0.14
    OMB
    -0.14
    zee
    -0.14
    Dot
    -0.14
    ué
    -0.14
    ëĨį
    -0.14
    POSITIVE LOGITS
     Stress
    0.24
     mesh
    0.23
     stress
    0.22
    stress
    0.22
     Finite
    0.21
     finite
    0.20
     meshes
    0.20
     Mesh
    0.20
     stresses
    0.19
    .mesh
    0.19
    Activations Density 0.044%

    No Known Activations