INDEX

Explanations

punctuation marks, specifically commas, in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ippo

-0.18

 therefore

-0.17

Ã§as

-0.16

inja

-0.16

ournÃ©e

-0.15

viso

-0.15

 indeed

-0.15

Ymd

-0.14

inand

-0.14

inosaur

-0.14

POSITIVE LOGITS

anch

0.14

ä»£çĲĨ

0.14

StandardItem

0.14

rightness

0.14

Å¼e

0.13

_CID

0.13

Ø³ØªØ§ÙĨ

0.13

ash

0.13

ze

0.13

Activations Density 0.034%

punctuation marks, specifically commas, in text

No Comments

No Known Activations