INDEX

Explanations

recurring conjunctions and words associated with conditionals or additional details in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

,alpha

-0.16

 airports

-0.15

 atoms

-0.15

 asteroids

-0.15

.Alpha

-0.14

 AIDS

-0.14

oure

-0.14

 Ã¡o

-0.14

.ArrayList

-0.14

âĹĭ

-0.14

POSITIVE LOGITS

urope

0.14

adress

0.14

ç¾

0.14

.iteritems

0.14

OLE

0.14

 å¾ĴæŃ©

0.14

 nonatomic

0.14

efeller

0.14

 disadvantages

0.13

ARC

0.13

Activations Density 0.199%

recurring conjunctions and words associated with conditionals or additional details in a text

No Comments

No Known Activations