INDEX

Explanations

phrases indicating possibilities and potential outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ernals

-0.16

ÑĸÑģÑĤÑĮ

-0.16

phinx

-0.16

chez

-0.16

edis

-0.15

-corner

-0.15

zcze

-0.15

roperty

-0.15

inee

-0.15

UPPORTED

-0.14

POSITIVE LOGITS

/pro

0.23

 outcomes

0.19

hood

0.19

/legal

0.19

 outcome

0.18

ment

0.18

 given

0.18

ity

0.17

mente

0.17

weise

0.17

Activations Density 0.065%

phrases indicating possibilities and potential outcomes

No Comments

No Known Activations