INDEX

Explanations

phrases that indicate intention or action towards achieving something

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

try

-0.20

Try

-0.20

try

-0.20

Try

-0.19

Ð¼ÐµÑĤÑĮ

-0.17

ssue

-0.16

dsa

-0.16

try

-0.15

icans

-0.15

 attempt

-0.15

POSITIVE LOGITS

 figure

0.21

 piece

0.20

 outr

0.20

 reason

0.19

 undue

0.17

 Piece

0.16

 interest

0.16

 guess

0.16

 find

0.16

fit

0.16

Activations Density 0.087%

phrases that indicate intention or action towards achieving something

No Comments

No Known Activations