INDEX

Explanations

phrases indicating uncertainty or conditional scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

/MPL

-0.17

antal

-0.17

hiba

-0.15

maz

-0.15

 çµĲ

-0.14

.xhtml

-0.14

Beg

-0.14

.synthetic

-0.14

Ø±Ø³ÛĮ

-0.14

 ãĥĽ

-0.14

POSITIVE LOGITS

Bundle

0.16

thon

0.15

.samples

0.15

 Watkins

0.15

adt

0.15

obb

0.14

ØªÛĮ

0.14

ildo

0.14

ey

0.14

Activations Density 0.298%

phrases indicating uncertainty or conditional scenarios

No Comments

No Known Activations