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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 18199
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of metrics and evaluative benchmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itoris
    -0.18
    bero
    -0.17
    andex
    -0.15
    atsby
    -0.15
    bstract
    -0.15
    @nate
    -0.15
    بÙĪØ§Ø³Ø·Ø©
    -0.15
    itori
    -0.15
    chandle
    -0.15
    ctica
    -0.15
    POSITIVE LOGITS
    ing
    1.55
    ed
    1.55
    ING
    0.86
    edBy
    0.80
    ers
    0.78
    edly
    0.75
    er
    0.74
    ings
    0.73
    able
    0.67
    ED
    0.67
    Activations Density 0.394%

    No Known Activations