INDEX

Explanations

dates and numerical references, particularly related to events or time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

onomic

-0.17

eenth

-0.17

nut

-0.17

een

-0.16

à¸£à¸£

-0.16

iterations

-0.15

steen

-0.15

Ð´Ð¸Ð½Ð°

-0.15

fer

-0.15

illum

-0.14

POSITIVE LOGITS

tere

0.19

inis

0.16

ials

0.16

ÙĦØ©

0.15

chg

0.15

allback

0.15

mer

0.14

UNCH

0.14

sole

0.14

å¤®

0.14

Activations Density 0.128%

dates and numerical references, particularly related to events or time periods

No Comments

No Known Activations