© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 7-LLAMASCOPE-RES-32K
    11. 19997
    Prev
    Next
    INDEX
    Explanations

    method definitions and structure in programming scripts, particularly in C# or similar languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rippling
    -0.17
    ÌĨ
    -0.16
    nze
    -0.16
    окон
    -0.15
    اÙĪÙĬØ©
    -0.15
    ansson
    -0.15
    Ìĥ
    -0.15
    thon
    -0.15
    ån
    -0.15
    stown
    -0.14
    POSITIVE LOGITS
    zb
    0.15
    erland
    0.14
     alike
    0.13
    леÑĤ
    0.13
    hab
    0.13
    alsy
    0.13
     Äijại
    0.13
    arten
    0.13
     sucker
    0.13
     Fitzgerald
    0.13
    Activations Density 0.001%

    No Known Activations