INDEX

Explanations

terms related to fellowships and collaboration among colleagues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

deal

-0.17

eland

-0.15

arak

-0.15

eln

-0.15

ÐºÐ¾Ð·

-0.15

alog

-0.15

ovel

-0.15

okers

-0.14

 meis

-0.14

pal

-0.14

POSITIVE LOGITS

ships

0.28

shipping

0.20

hood

0.18

iped

0.16

ship

0.15

SHIP

0.15

iesen

0.15

ods

0.15

exion

0.15

ç¨ĭ

0.14

Activations Density 0.012%

terms related to fellowships and collaboration among colleagues

No Comments

No Known Activations