INDEX

Explanations

programming constructs and structures related to data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

illus

-0.15

canf

-0.15

oningen

-0.15

far

-0.14

?action

-0.14

è¦

-0.14

+]

-0.14

(true

-0.14

anzi

-0.14

 Calc

-0.13

POSITIVE LOGITS

.scalablytyped

0.18

 False

0.17

etus

0.17

 None

0.16

**

0.16

 mode

0.16

 force

0.16

 QtCore

0.15

 verbose

0.15

FRING

0.15

Activations Density 0.057%

programming constructs and structures related to data processing

No Comments

No Known Activations