INDEX

Explanations

numerical data related to organizations and their operations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

vÃ¡

-0.16

 Feder

-0.15

ozo

-0.15

adow

-0.15

hta

-0.14

Voj

-0.14

ABCDEFGHIJKLMNOP

-0.14

ÅĻez

-0.13

.IC

-0.13

nez

-0.13

POSITIVE LOGITS

Sal

0.17

tainment

0.16

ÙĦÙĬÙħ

0.16

 Employment

0.15

sal

0.15

olders

0.15

Sal

0.15

 employment

0.15

VS

0.14

bor

0.14

Activations Density 0.000%

numerical data related to organizations and their operations

No Known Activations