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. 31-LLAMASCOPE-RES-32K
    6. 30995
    Prev
    Next
    INDEX
    Explanations

    references to digital content creation and local versus global market dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plá
    -0.12
    ãĥ³ãĥ
    -0.11
    Ư
    -0.11
    ransition
    -0.11
    ankind
    -0.10
     menstr
    -0.10
    strom
    -0.10
    šen
    -0.10
     Ñĥмов
    -0.10
     èIJ¬
    -0.10
    POSITIVE LOGITS
     local
    1.20
    local
    1.02
     Local
    0.99
     LOCAL
    0.98
     locally
    0.98
     locals
    0.97
    -local
    0.96
    Local
    0.93
     lokal
    0.90
    _local
    0.88
    Activations Density 0.264%

    No Known Activations