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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 28363
    Prev
    Next
    INDEX
    Explanations

    references to community and organizational entities related to sport and recreation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    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
    -0.16
     principalTable
    -0.15
    ỳ
    -0.14
    specs
    -0.13
    SYS
    -0.13
    upiter
    -0.13
    send
    -0.12
     Ä
    -0.12
    sel
    -0.12
    çŁ
    -0.12
    POSITIVE LOGITS
    ÂłS
    0.23
     S
    0.22
    _S
    0.22
     ãĤ¹
    0.20
     स
    0.20
     س
    0.20
    _sb
    0.19
    	S
    0.19
    Âłs
    0.18
    _s
    0.18
    Activations Density 0.381%

    No Known Activations