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. 5-LLAMASCOPE-RES-32K
    6. 205
    Prev
    Next
    INDEX
    Explanations

    technical terms related to neural networks and optimization algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignet
    -0.21
    ãĥ¼ãĥĦ
    -0.17
    è¼
    -0.17
    ãĥ¥
    -0.16
    .har
    -0.16
    udget
    -0.16
    Ñİк
    -0.15
     dro
    -0.14
    chez
    -0.14
     Dropbox
    -0.14
    POSITIVE LOGITS
    iasi
    0.18
    lingen
    0.16
    holm
    0.16
    obel
    0.16
    Mari
    0.15
     Mari
    0.15
    ÑĥÑĢÑĥ
    0.15
    ereg
    0.14
    oling
    0.14
    atha
    0.14
    Activations Density 0.011%

    No Known Activations