INDEX

Explanations

punctuation marks and formatting elements within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-0.19

-0.17

-0.16

Bak

-0.16

Inn

-0.15

ies

-0.15

iese

-0.14

POSITIVE LOGITS

 INTERRUPTION

0.17

_UNUSED

0.17

Ãłm

0.16

astle

0.16

(éĩĳ

0.16

APTER

0.15

 NEGLIGENCE

0.15

 OTHERWISE

0.15

ç«ľ

0.14

Ð¼Ð°Ñħ

0.14

Activations Density 0.040%

punctuation marks and formatting elements within the text

No Comments

No Known Activations