INDEX

Explanations

words that end with "ing."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

unny

-0.17

bron

-0.16

ifa

-0.16

eth

-0.15

nds

-0.15

skl

-0.15

ÑĭÑģ

-0.14

ogne

-0.14

reira

-0.14

uger

-0.14

POSITIVE LOGITS

oment

0.17

urv

0.15

polator

0.14

Ø±Ø§Øª

0.14

animations

0.14

Ð»Ð°Ð²Ð°

0.14

áº¡m

0.14

ustry

0.14

amaha

0.14

Ä±ÅŁÄ±k

0.13

Activations Density 0.004%

words that end with "ing."

No Comments

No Known Activations