INDEX

Explanations

terms related to scientific phenomena, specifically those involving light and waves

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

itori

-0.16

ataka

-0.16

onia

-0.15

uling

-0.15

itur

-0.14

 Dynamics

-0.14

dera

-0.14

achuset

-0.13

ellites

-0.13

_transient

-0.13

POSITIVE LOGITS

 traveling

0.35

 travelling

0.34

 propag

0.32

travel

0.28

 sent

0.28

 travel

0.28

 passing

0.26

 travels

0.26

 Travel

0.25

 hitting

0.25

Activations Density 0.161%

terms related to scientific phenomena, specifically those involving light and waves

No Comments

No Known Activations