INDEX

Explanations

temporal markers and related expressions 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

agal

-0.18

deÅŁ

-0.18

ÄĽnÃŃ

-0.17

zo

-0.16

anch

-0.15

fal

-0.15

ç¥ĸ

-0.15

ackages

-0.15

agi

-0.15

vÄĽdom

-0.15

POSITIVE LOGITS

eri

0.18

kit

0.17

 Grey

0.16

erb

0.16

 Hack

0.15

 Hort

0.15

IRE

0.15

CEE

0.15

Kit

0.14

 recreate

0.14

Activations Density 0.138%

temporal markers and related expressions within the text

No Comments

No Known Activations