INDEX

Explanations

words related to skepticism and doubt, especially in contexts involving ghosts, aliens, and other supernatural phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

asco

-0.16

illas

-0.16

airo

-0.16

brahim

-0.15

è¢ĭ

-0.14

excerpt

-0.14

ÙİÙģ

-0.14

ainer

-0.14

nga

-0.14

ãĥ³ãĤ°

-0.14

POSITIVE LOGITS

letal

0.24

chers

0.21

logg

0.15

orting

0.15

irsch

0.15

elm

0.15

MSN

0.15

inesis

0.15

ington

0.14

raf

0.14

Activations Density 0.009%

words related to skepticism and doubt, especially in contexts involving ghosts, aliens, and other supernatural phenomena

No Comments

No Known Activations