© 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. 15-LLAMASCOPE-RES-32K
    11. 2283
    Prev
    Next
    INDEX
    Explanations

    elements of sequential progression or comparison in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reversed
    -0.16
     reverse
    -0.15
    olit
    -0.15
    unca
    -0.15
    mez
    -0.15
    .reverse
    -0.15
    invert
    -0.15
     separately
    -0.14
    .ut
    -0.14
     separate
    -0.14
    POSITIVE LOGITS
     next
    0.31
    next
    0.28
    _next
    0.27
     à¤ħà¤Ĺल
    0.27
     ëĭ¤ìĿĮ
    0.26
    ,next
    0.26
     getNext
    0.25
     Next
    0.25
     NEXT
    0.25
    (next
    0.24
    Activations Density 0.243%

    No Known Activations