INDEX

Explanations

phrases indicating indifference or a lack of specific preference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ses

-0.20

sb

-0.17

sil

-0.17

sid

-0.16

sj

-0.15

ryn

-0.15

.scalablytyped

-0.15

Ð½ÐµÐ½

-0.15

sst

-0.15

mund

-0.15

POSITIVE LOGITS

 else

0.21

theless

0.21

ly

0.18

anged

0.17

anging

0.16

thing

0.16

ity

0.16

Æ¡

0.16

rr

0.16

Activations Density 0.016%

phrases indicating indifference or a lack of specific preference

No Comments

No Known Activations