INDEX

Explanations

references to leadership roles and titles associated with leading positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

esser

-0.16

Ã£i

-0.15

ico

-0.15

otope

-0.15

alles

-0.14

olle

-0.14

kowski

-0.14

ì§Ŀ

-0.14

kov

-0.14

POSITIVE LOGITS

/main

0.16

tember

0.14

/Main

0.14

å¹¹ç·ļ

0.14

ÑĪÑĤ

0.14

sembly

0.14

ÙĬØ±ÙĬ

0.14

çŃĴ

0.13

Ral

0.13

ully

0.13

Activations Density 0.033%

references to leadership roles and titles associated with leading positions

No Comments

No Known Activations