INDEX

Explanations

references to academic citations and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

all

-0.23

none

-0.20

(all

-0.17

 none

-0.16

ippi

-0.16

ALL

-0.16

erre

-0.15

 Chow

-0.15

None

-0.15

all

-0.15

POSITIVE LOGITS

eds

0.23

 themselves

0.19

eds

0.19

duo

0.16

 Ð¾Ð±Ð¾

0.16

Ø§Ø³Ø§ÙĨ

0.16

Duo

0.16

.BLL

0.15

 ambos

0.15

ä¸¤äºº

0.15

Activations Density 0.045%

references to academic citations and publications

No Comments

No Known Activations