INDEX

Explanations

phrases related to achieving tasks and results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÃŃ

-0.16

ington

-0.15

eted

-0.15

ies

-0.15

ys

-0.15

Ste

-0.14

azzo

-0.14

for

-0.14

ay

-0.14

ista

-0.14

POSITIVE LOGITS

rid

0.21

ework

0.18

chas

0.18

efon

0.17

ahl

0.16

 started

0.16

hold

0.16

oby

0.16

ovah

0.16

zell

0.16

Activations Density 0.108%

phrases related to achieving tasks and results

No Comments

No Known Activations