Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 21973
    Prev
    Next
    INDEX
    Explanations

    references to tea and related beverages

    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
    mente
    -0.17
     lock
    -0.17
    eds
    -0.16
     Humb
    -0.16
    mes
    -0.15
    edList
    -0.15
    i
    -0.15
    tra
    -0.15
    so
    -0.15
    ry
    -0.15
    POSITIVE LOGITS
    asaki
    0.18
    ÑģÑĤоÑĢ
    0.17
    idlo
    0.16
    UCKET
    0.15
    ÎŃÏģα
    0.15
    Æ°á»Ľng
    0.15
    ÅĻenÃŃ
    0.15
    wire
    0.15
    illon
    0.15
    Pid
    0.15
    Activations Density 0.010%

    No Known Activations