INDEX

Explanations

questions and phrases about the effectiveness of actions or efforts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

gest

-0.20

GEST

-0.15

eo

-0.15

 ÑĤÑĢÑĥ

-0.15

åºŃ

-0.14

abor

-0.14

 Simpl

-0.14

STD

-0.13

elig

-0.13

ismic

-0.13

POSITIVE LOGITS

 Guards

0.15

bara

0.15

.toObject

0.14

quez

0.14

 Pawn

0.13

zk

0.13

ForObject

0.13

Î¯Î¸

0.13

ddy

0.13

anos

0.13

Activations Density 0.104%

questions and phrases about the effectiveness of actions or efforts

No Comments

No Known Activations