INDEX

Explanations

references related to software components and their versions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ÑĢÐµÐ±

-0.16

ARB

-0.16

à¤¾à¤¦à¤¨

-0.15

kova

-0.14

.getColumnIndex

-0.14

lob

-0.14

avers

-0.14

æ´ĭ

-0.13

-FIRST

-0.13

 wealthiest

-0.13

POSITIVE LOGITS

aign

0.20

idy

0.16

Ð¿Ð¾Ñĩ

0.16

ãĤ¢ãĥ¼

0.15

 Anch

0.15

fst

0.15

essen

0.14

/dc

0.14

0.13

uish

0.13

Activations Density 0.036%

references related to software components and their versions

No Comments

No Known Activations

references related to software components and their versions

No Comments

No Known Activations