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

    Neuronpedia

    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. 16-LLAMASCOPE-RES-32K
    11. 20899
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     never
    -0.16
     sort
    -0.15
    etten
    -0.15
    abin
    -0.15
     leg
    -0.14
    aram
    -0.14
     hope
    -0.14
    áhl
    -0.14
    ozilla
    -0.14
    ãģıãĤĭ
    -0.14
    POSITIVE LOGITS
     currently
    0.29
    currently
    0.28
     aktu
    0.26
     presently
    0.25
    Currently
    0.25
     tonight
    0.24
     Currently
    0.24
     current
    0.24
    å½ĵåīį
    0.24
     íĺĦìŀ¬
    0.23
    Activations Density 0.202%

    No Known Activations