INDEX

Explanations

references to specific individuals and organizations in a news context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

/bower

-0.15

otu

-0.14

.GroupLayout

-0.14

_FRAMEBUFFER

-0.14

cts

-0.14

 lands

-0.14

ãĥ¶æľĪ

-0.14

arov

-0.14

 flipped

-0.14

.fm

-0.14

POSITIVE LOGITS

 Reuters

0.40

Reuters

0.35

 REUTERS

0.33

 Thomson

0.23

UTERS

0.19

Reporting

0.18

opak

0.17

_lineno

0.16

.Reporting

0.15

/File

0.15

Activations Density 0.031%

references to specific individuals and organizations in a news context

No Comments

No Known Activations