© 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. 18-LLAMASCOPE-RES-32K
    11. 24841
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate purpose or function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apat
    -0.17
    iec
    -0.15
    916
    -0.15
    ÑģÑĮ
    -0.15
    ateria
    -0.14
    -ÑĤ
    -0.14
    TagName
    -0.14
    avors
    -0.14
    isque
    -0.14
    ContentLoaded
    -0.13
    POSITIVE LOGITS
     action
    0.18
    Enumerable
    0.17
     attack
    0.17
    Docs
    0.16
    operation
    0.14
    hi
    0.14
     operation
    0.14
    ãģ¯ãģªãģĦ
    0.14
    chied
    0.14
     interest
    0.14
    Activations Density 0.143%

    No Known Activations