INDEX

Explanations

numerical values or references to time-related metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Walters

-0.18

StatusLabel

-0.15

ÐµÑģÑı

-0.15

eview

-0.14

 baÄŁlantÄ±lar

-0.13

less

-0.13

beer

-0.13

stown

-0.13

weis

-0.13

erson

-0.13

POSITIVE LOGITS

eldon

0.16

aldi

0.13

(Of

0.13

/todo

0.13

 whole

0.13

¢åįķ

0.13

ãĤ¸ãĤ¢

0.13

ths

0.13

%;">

0.13

Activations Density 0.071%

numerical values or references to time-related metrics

No Comments

No Known Activations