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. 10-LLAMASCOPE-RES-32K
    6. 9238
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     evidenced
    -0.22
    otten
    -0.17
    alls
    -0.17
    販
    -0.17
    ãģªãģĮãĤī
    -0.15
    HORT
    -0.14
    bindung
    -0.14
    kate
    -0.14
    inç
    -0.14
     Evidence
    -0.14
    POSITIVE LOGITS
    paragus
    0.23
    cribed
    0.21
    cert
    0.21
    cribing
    0.21
    phy
    0.21
     opposed
    0.20
    sembl
    0.18
    cribe
    0.18
     part
    0.18
     regards
    0.18
    Activations Density 0.312%

    No Known Activations