INDEX

Explanations

names of authors and their affiliations or credentials in a publication context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

incinn

-0.15

.ToolTip

-0.13

 epic

-0.13

wick

-0.13

yclopedia

-0.13

ynos

-0.13

.smtp

-0.13

 Scratch

-0.12

(;

-0.12

Ð¼ÐµÑĪ

-0.12

POSITIVE LOGITS

utow

0.16

APT

0.15

Sensitive

0.15

orsi

0.14

alli

0.14

acÃŃ

0.14

Ãľ

0.14

ä¸įå®ī

0.14

_capabilities

0.13

çĮ

0.13

Activations Density 0.003%

names of authors and their affiliations or credentials in a publication context

No Comments

No Known Activations