INDEX

Explanations

key terms related to educational contexts and processes

oai_token-act-pair · gpt-4o-mini Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eker

-0.21

Gem

-0.17

uni

-0.15

 Vand

-0.15

aken

-0.15

 stat

-0.14

opper

-0.14

bs

-0.14

AKER

-0.14

bs

-0.14

POSITIVE LOGITS

Unhandled

0.16

Owned

0.16

enty

0.15

 Owned

0.14

FRING

0.14

orre

0.14

ÙĪØ¬ÙĪØ¯

0.14

ippets

0.14

ContentAlignment

0.14

yntax

0.14

Activations Density 0.004%

key terms related to educational contexts and processes

No Comments

No Known Activations