INDEX

Explanations

time and date information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

inem

-0.17

Ð±Ð°Ñĩ

-0.17

upro

-0.16

holm

-0.15

baugh

-0.15

ative

-0.15

Ŀ

-0.14

amps

-0.14

inear

-0.14

asant

-0.14

POSITIVE LOGITS

Uhr

0.19

UTC

0.17

zon

0.17

UTC

0.16

ìĭľ

0.15

uur

0.15

0.14

ìĭľìĹĲ

0.14

dzi

0.14

aku

0.14

Activations Density 0.066%

time and date information

No Comments

No Known Activations