© 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. 27-LLAMASCOPE-RES-32K
    11. 11923
    Prev
    Next
    INDEX
    Explanations

    terms related to health and the effects of herbal remedies on bodily functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vant
    -0.16
    rof
    -0.15
    omed
    -0.15
    .magic
    -0.15
    adx
    -0.14
    nesc
    -0.14
    -validation
    -0.14
    itis
    -0.13
    -visible
    -0.13
     bất
    -0.13
    POSITIVE LOGITS
     circulation
    0.23
     functioning
    0.23
     appetite
    0.22
     blood
    0.21
     immune
    0.21
     function
    0.21
     mot
    0.21
    mentation
    0.21
     metabolism
    0.20
     vital
    0.19
    Activations Density 0.221%

    No Known Activations