INDEX

Explanations

terms related to maritime and underwater environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ä¿

-0.18

çīĩ

-0.15

OMET

-0.15

stype

-0.15

stile

-0.14

zo

-0.14

plib

-0.14

 GenerationType

-0.14

 jadx

-0.14

sei

-0.14

POSITIVE LOGITS

/off

0.25

/on

0.24

/down

0.21

/out

0.20

/back

0.17

/front

0.16

ers

0.16

 wind

0.15

/up

0.15

-bound

0.15

Activations Density 0.054%

terms related to maritime and underwater environments

No Comments

No Known Activations