INDEX

Explanations

words related to venerable or respected figures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

_REFRESH

-0.15

pulse

-0.14

 bond

-0.14

å¼ĺ

-0.14

xlim

-0.14

itto

-0.14

ilion

-0.14

anlar

-0.14

Ã¼zel

-0.14

ullivan

-0.13

POSITIVE LOGITS

akin

0.16

lag

0.15

er

0.15

 prospects

0.15

ores

0.15

 Bender

0.14

rous

0.14

vision

0.14

ipo

0.14

Activations Density 0.005%

words related to venerable or respected figures

No Comments

No Known Activations