INDEX

Explanations

formal and structured elements within legal or regulatory documents

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ÑĦÑĦ

-0.15

olare

-0.15

ivic

-0.15

ochrome

-0.15

 Harr

-0.14

MMdd

-0.14

oyal

-0.14

ÐĲÑĢÑħÑĸÐ²Ð¾Ð²Ð°Ð½Ð¾

-0.13

.toFloat

-0.13

POSITIVE LOGITS

 factor

0.15

ç¾½

0.15

 Factor

0.15

spiel

0.15

æ³

0.15

Dow

0.14

FIT

0.14

 unfit

0.14

alist

0.14

-factor

0.14

Activations Density 0.110%

formal and structured elements within legal or regulatory documents

No Comments

No Known Activations