INDEX

Explanations

references to slowness or gradualness in actions or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

alat

-0.16

chw

-0.16

laÅŁ

-0.16

onte

-0.16

 tÃ¡

-0.15

ulet

-0.15

iled

-0.15

-0.14

erap

-0.14

POSITIVE LOGITS

poke

0.36

-motion

0.27

-paced

0.27

 paced

0.26

est

0.25

ww

0.25

paced

0.23

inski

0.23

æħ¢

0.23

-moving

0.23

Activations Density 0.017%

references to slowness or gradualness in actions or descriptions

No Comments

No Known Activations