INDEX

Explanations

expressions of uncertainty or doubt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

rio

-0.16

ermen

-0.15

*)_

-0.15

SizeMode

-0.15

.googleapis

-0.15

Ã©ric

-0.15

Ð¿ÑĢÐ°

-0.14

inki

-0.14

erness

-0.14

 Metals

-0.14

POSITIVE LOGITS

any

0.21

nor

0.18

 anyone

0.17

arte

0.17

 anymore

0.17

Nor

0.17

any

0.16

 anything

0.16

ope

0.16

quot

0.16

Activations Density 0.136%

expressions of uncertainty or doubt

No Comments

No Known Activations