INDEX

Explanations

occurrences of tags or labels 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 @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

undi

-0.17

indo

-0.16

kaar

-0.15

Hoe

-0.15

à¥įà¤¤à¤¨

-0.15

 Robbins

-0.14

.ht

-0.14

band

-0.14

ibold

-0.14

eb

-0.14

POSITIVE LOGITS

alia

0.18

0.15

0.14

æķ

0.14

entic

0.14

ewise

0.14

ethod

0.14

Ans

0.13

ansk

0.13

Activations Density 0.006%

occurrences of tags or labels within the text

No Comments

No Known Activations