INDEX

Explanations

structured data points and references within legal or formal agreements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

IBC

-0.16

ÙĤÛĮ

-0.15

ëģ¼

-0.14

er

-0.13

PLAIN

-0.13

/=

-0.13

ucu

-0.13

NBC

-0.13

ata

-0.13

iba

-0.13

POSITIVE LOGITS

adoras

0.16

ÅĻil

0.16

bens

0.16

 neod

0.16

adora

0.15

EFR

0.15

arily

0.14

essler

0.14

inals

0.14

ãĥ¨

0.14

Activations Density 0.039%

structured data points and references within legal or formal agreements

No Known Activations