INDEX

Explanations

mentions of additional items or features that enhance or add value to a product or experience

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

.gdx

-0.15

 BASIS

-0.15

/System

-0.14

 Ð²ÐµÐ»

-0.14

/bower

-0.14

ifr

-0.14

/Base

-0.13

rica

-0.13

Dum

-0.13

 Basis

-0.13

POSITIVE LOGITS

ordinary

0.21

UBLE

0.16

kus

0.15

rows

0.15

hey

0.15

allee

0.15

endum

0.15

-extra

0.15

Ä±ÅŁÄ±k

0.14

ãĥ¼ãĥī

0.14

Activations Density 0.013%

mentions of additional items or features that enhance or add value to a product or experience

No Comments

No Known Activations