© 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. 30-LLAMASCOPE-RES-32K
    11. 18141
    Prev
    Next
    INDEX
    Explanations

    references to elements of technology, particularly programming concepts and software components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fourth
    -0.31
     fifth
    -0.30
     sixth
    -0.30
     seventh
    -0.30
     ninth
    -0.29
     eighth
    -0.28
     tenth
    -0.25
     Sixth
    -0.25
     Seventh
    -0.24
     Ninth
    -0.24
    POSITIVE LOGITS
    2
    1.03
    Û²
    0.66
    ï¼Ĵ
    0.63
    âĤĤ
    0.57
    äºĮ
    0.56
    ²
    0.54
     äºĮ
    0.52
     Two
    0.49
    02
    0.49
    -two
    0.48
    Activations Density 0.609%

    No Known Activations