© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 20-LLAMASCOPE-RES-32K
    11. 31774
    Prev
    Next
    INDEX
    Explanations

    terms related to structure and hierarchy in reporting or discussing communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     as
    -0.34
     als
    -0.30
     sebagai
    -0.26
     jako
    -0.25
     как
    -0.23
    ä½ľä¸º
    -0.22
    ongan
    -0.19
    为
    -0.18
    	as
    -0.18
     ako
    -0.18
    POSITIVE LOGITS
    ãĤ¶ãĥ¼
    0.15
    364
    0.14
     Weiner
    0.14
    wis
    0.14
    xdc
    0.13
    usunda
    0.13
    .yy
    0.13
     unto
    0.13
    uyết
    0.13
    oulos
    0.13
    Activations Density 0.236%

    No Known Activations