INDEX

Explanations

phrases or words related to the concept of "up."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

UGIN

-0.18

 Rosenstein

-0.15

amespace

-0.15

VERR

-0.15

fkk

-0.14

aÄį

-0.14

ÅĻed

-0.14

eam

-0.14

ÐµÑī

-0.14

******/

-0.14

POSITIVE LOGITS

mlink

0.16

nn

0.15

bler

0.14

own

0.14

rightness

0.14

Ð²Ð°Ð¶

0.14

 Orig

0.14

Dos

0.14

oir

0.14

Ĭ

0.14

Activations Density 0.158%

phrases or words related to the concept of "up."

No Comments

No Known Activations