INDEX

Explanations

dates and financial year references

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ennie

-0.14

itzer

-0.14

 absolute

-0.14

cdf

-0.14

-0.13

 Rolls

-0.13

Ã¡f

-0.13

Ð½Ð¸Ñĩ

-0.13

orro

-0.13

 backward

-0.13

POSITIVE LOGITS

unday

0.19

ape

0.18

ogui

0.17

ushima

0.15

idden

0.15

prite

0.15

owitz

0.14

ccione

0.14

IBC

0.14

asaki

0.14

Activations Density 0.066%

dates and financial year references

No Comments

No Known Activations