INDEX

Explanations

file path notations and related syntax

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

isa

-0.15

osto

-0.14

ÅĤ

-0.14

imeo

-0.14

ns

-0.14

.Accessible

-0.13

Ð°Ð½Ðº

-0.13

SV

-0.13

ĶåĽŀ

-0.13

ÐµÑģÑĮ

-0.13

POSITIVE LOGITS

isson

0.17

 theme

0.16

ispens

0.16

ÏģÎ¿Ïį

0.15

 EXPER

0.15

aison

0.15

phans

0.15

ÙĩÙĦ

0.15

ovit

0.14

omik

0.14

Activations Density 0.039%

file path notations and related syntax

No Comments

No Known Activations