INDEX

Explanations

phrases indicating comparison or similarity among items or people

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

quil

-0.15

marshall

-0.15

ober

-0.15

á»¥y

-0.14

á»¥

-0.14

ebb

-0.14

LSB

-0.13

PointerException

-0.13

.platform

-0.13

POSITIVE LOGITS

WEEN

0.18

 alike

0.17

 Heck

0.16

eler

0.15

lier

0.14

NDER

0.14

 Bulk

0.14

bracht

0.14

 merit

0.14

 proper

0.14

Activations Density 0.322%

phrases indicating comparison or similarity among items or people

No Comments

No Known Activations