INDEX

Explanations

terms related to fast food

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.16

ONT

-0.15

quent

-0.15

 puta

-0.15

ijd

-0.15

ieu

-0.15

iso

-0.15

ont

-0.14

Æ¡n

-0.14

abant

-0.14

POSITIVE LOGITS

erville

0.17

AffineTransform

0.14

apter

0.14

ÄįÃŃ

0.14

itsu

0.14

.Unsupported

0.14

ëłĪìĿ´

0.14

<!--[

0.13

ampus

0.13

ÑıÐ¼

0.13

Activations Density 0.006%

terms related to fast food

No Comments

No Known Activations