INDEX

Explanations

references to historical world conflicts and their respective durations or designations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 first

-0.17

addtogroup

-0.17

egin

-0.16

 second

-0.15

ãĥ³ãĥ

-0.15

epar

-0.14

oris

-0.14

overrides

-0.14

 fourth

-0.14

ighth

-0.14

POSITIVE LOGITS

OLUME

0.17

 Ø¹Ø´Ø±

0.17

 Flush

0.17

arily

0.17

-tier

0.16

 division

0.16

 flush

0.16

 phase

0.16

 volume

0.16

Activations Density 0.083%

references to historical world conflicts and their respective durations or designations

No Comments

No Known Activations