INDEX

Explanations

phrases related to warranties and product satisfaction issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ancode

-0.17

weis

-0.16

ouri

-0.16

ures

-0.15

aries

-0.15

à¹Ģà¸Ħà¸¥

-0.15

aterno

-0.15

inho

-0.14

_ut

-0.14

ined

-0.14

POSITIVE LOGITS

HEMA

0.18

wy

0.14

otionEvent

0.14

ohn

0.14

Ø¨ÙĨ

0.14

imus

0.13

 Hlav

0.13

 tÃ´n

0.13

reopen

0.13

VertexBuffer

0.13

Activations Density 0.290%

phrases related to warranties and product satisfaction issues

No Comments

No Known Activations