INDEX

Explanations

negations and assertions that challenge common beliefs or misconceptions

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

.Apis

-0.18

iger

-0.16

berger

-0.16

zan

-0.16

wyn

-0.15

 Faker

-0.15

 Pais

-0.15

heels

-0.14

shr

-0.14

POSITIVE LOGITS

 anymore

0.21

nor

0.16

 today

0.16

ItemSelected

0.15

uti

0.14

ob

0.14

 inter

0.14

as

0.14

ab

0.14

Activations Density 0.066%

negations and assertions that challenge common beliefs or misconceptions

No Comments

No Known Activations