INDEX

Explanations

instances of quotation marks and references to beliefs or opinions

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

ppelin

-0.17

ãĥ¼ãĥł

-0.16

InputGroup

-0.14

.setViewport

-0.14

oso

-0.14

_DDR

-0.13

ladu

-0.13

-Ð¿ÑĢÐ°Ð²

-0.13

ahkan

-0.13

andre

-0.13

POSITIVE LOGITS

 Reporter

0.15

 Abstract

0.15

 Mint

0.15

ukes

0.14

ela

0.14

uar

0.14

uya

0.14

iel

0.13

 unspecified

0.13

@d

0.13

Activations Density 0.200%

instances of quotation marks and references to beliefs or opinions

No Comments

No Known Activations