INDEX

Explanations

expressions of desire or intention related to preferences and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

isma

-0.21

pedia

-0.18

doz

-0.17

eless

-0.15

swick

-0.15

vrier

-0.14

addock

-0.14

ÄĻd

-0.14

Çİ

-0.14

uming

-0.14

POSITIVE LOGITS

 else

0.21

who

0.20

 except

0.19

 Except

0.17

except

0.16

 whom

0.16

who

0.15

Except

0.15

 including

0.15

è°ģ

0.15

Activations Density 0.093%

expressions of desire or intention related to preferences and actions

No Comments

No Known Activations