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. 18003
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, particularly cities and states

    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
    ģm
    -0.17
    altar
    -0.16
    atte
    -0.15
     borderTop
    -0.15
    ãĥ«ãĥķ
    -0.15
    athed
    -0.15
     Peel
    -0.15
    entes
    -0.14
     cro
    -0.14
     niên
    -0.14
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.15
    èĴĤ
    0.15
    sha
    0.15
    baum
    0.15
    .Pointer
    0.14
    force
    0.14
    FORCE
    0.14
    icare
    0.14
    hello
    0.14
    uest
    0.14
    Activations Density 0.102%

    No Known Activations