INDEX

Explanations

repetitions and variations of the word "that" in different contexts

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

icz

-0.17

Peg

-0.15

uzu

-0.14

croft

-0.14

earable

-0.14

riad

-0.14

kyt

-0.13

icle

-0.13

sac

-0.13

ocker

-0.13

POSITIVE LOGITS

 Sexo

0.17

zzle

0.16

ivec

0.15

abbo

0.15

akin

0.14

otland

0.14

semi

0.14

-vs

0.14

anson

0.14

 Ø¨ÙĪØ§Ø¨Ø©

0.14

Activations Density 0.148%

repetitions and variations of the word "that" in different contexts

No Comments

No Known Activations