INDEX

Explanations

references to various types of prizes and awards

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

zcze

-0.16

ungal

-0.16

itte

-0.15

ispecies

-0.15

unge

-0.15

izard

-0.14

urgy

-0.14

mÃŃt

-0.14

·

-0.14

itle

-0.14

POSITIVE LOGITS

ois

0.19

icari

0.16

.raises

0.15

OLUME

0.15

anova

0.14

pmat

0.14

yro

0.14

pawn

0.14

 emulation

0.14

actly

0.14

Activations Density 0.005%

references to various types of prizes and awards

No Comments

No Known Activations