INDEX

Explanations

references to the "Star Trek: The Next Generation" series and its characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

egin

-0.19

[".

-0.15

UTES

-0.15

tier

-0.15

_TER

-0.14

omik

-0.14

ascar

-0.14

 next

-0.14

ynch

-0.14

ARGET

-0.14

POSITIVE LOGITS

qua

0.16

ãĥĭãĤ¢

0.15

uren

0.15

Ã±a

0.14

 Locker

0.14

allon

0.14

ick

0.14

,var

0.13

ptype

0.13

arf

0.13

Activations Density 0.025%

references to the "Star Trek: The Next Generation" series and its characters

No Comments

No Known Activations