© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 17699
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to eye health and degenerative eye diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĩĮ
    -0.17
    .classes
    -0.15
    728
    -0.14
     citas
    -0.14
    omo
    -0.14
    .addHandler
    -0.14
    avic
    -0.14
     Lun
    -0.14
     rooting
    -0.13
     Nem
    -0.13
    POSITIVE LOGITS
     mac
    0.30
     ret
    0.29
     retina
    0.26
     Mac
    0.23
    mac
    0.23
    _mac
    0.23
    Mac
    0.22
     AMD
    0.22
    (mac
    0.22
    _ret
    0.21
    Activations Density 0.007%

    No Known Activations