INDEX

Explanations

expressions of "purpose" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.20

act

-0.16

ëĿ½

-0.16

ey

-0.15

inja

-0.15

rec

-0.14

ruta

-0.14

.isNullOrEmpty

-0.14

ath

-0.14

kest

-0.14

POSITIVE LOGITS

fully

0.26

ful

0.23

lessly

0.19

-built

0.17

FUL

0.17

full

0.16

fulness

0.16

pendicular

0.16

quoi

0.15

anker

0.15

Activations Density 0.020%

expressions of "purpose" in various contexts

No Comments

No Known Activations