© 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. 29-LLAMASCOPE-RES-32K
    11. 12272
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to gaming terminology and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /Sub
    -0.20
    sync
    -0.19
    =sub
    -0.17
    splice
    -0.17
    serviceName
    -0.17
    snippet
    -0.17
     Spreadsheet
    -0.17
    ska
    -0.17
     submissive
    -0.16
    smith
    -0.16
    POSITIVE LOGITS
    -s
    1.03
    -S
    0.83
    Âłs
    0.68
    _S
    0.64
    ÂłS
    0.63
    _s
    0.57
    	S
    0.56
    	s
    0.51
    =s
    0.47
    ãĤµ
    0.47
    Activations Density 0.776%

    No Known Activations