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. 17-LLAMASCOPE-RES-32K
    6. 26800
    Prev
    Next
    INDEX
    Explanations

    key terminology and phrases related to data analysis and benchmarking methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etc
    -0.17
    (and
    -0.16
    iken
    -0.14
    &M
    -0.14
    fak
    -0.14
    .Îij
    -0.14
    arger
    -0.14
     etc
    -0.14
    çŃī
    -0.14
    ","","
    -0.13
    POSITIVE LOGITS
    ãĤĵãģ¨
    0.22
     ìŀĪê³ł
    0.19
     oraz
    0.19
    ï¼Į以åıĬ
    0.19
     versus
    0.18
     à¹ģละ
    0.18
     AND
    0.17
     and
    0.17
    )&&
    0.17
     ãģ¨
    0.16
    Activations Density 0.540%

    No Known Activations