© 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. 27-LLAMASCOPE-RES-32K
    6. 2820
    Prev
    Next
    INDEX
    Explanations

    products and features related to personal care and beauty

    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
     rank
    -0.16
    á»Ļp
    -0.16
    oten
    -0.16
     Rank
    -0.16
     Hurt
    -0.15
    rollo
    -0.15
    Rank
    -0.15
     vh
    -0.15
     serm
    -0.14
    ussy
    -0.14
    POSITIVE LOGITS
     faucet
    0.28
     fauc
    0.28
     Fauc
    0.28
     sink
    0.22
     tap
    0.22
    Sink
    0.22
     taps
    0.22
     Chrome
    0.22
    .delta
    0.21
     brass
    0.21
    Activations Density 0.012%

    No Known Activations