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. 13-LLAMASCOPE-RES-32K
    6. 15397
    Prev
    Next
    INDEX
    Explanations

    expressions related to accumulation or organization of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adle
    -0.16
     ConfigureServices
    -0.16
     Kurd
    -0.15
    eco
    -0.14
     Fab
    -0.14
    ubo
    -0.14
    assel
    -0.13
    اÙĤ
    -0.13
    .timeline
    -0.13
    ittel
    -0.13
    POSITIVE LOGITS
    hammer
    0.17
    verage
    0.17
    lej
    0.16
    erset
    0.16
    alama
    0.15
    chair
    0.15
     pile
    0.14
     stack
    0.14
    -sama
    0.14
    pile
    0.14
    Activations Density 0.050%

    No Known Activations