INDEX

Explanations

references to interviews and conversations about films and their creators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Bald

-0.15

OGLE

-0.15

æ¯Ľ

-0.14

 taÅŁÄ±m

-0.14

standing

-0.14

 ÑģÐ¸

-0.14

imulator

-0.14

 BaseType

-0.14

crap

-0.14

 Carlson

-0.13

POSITIVE LOGITS

inet

0.16

/INFO

0.15

æ°£

0.14

hone

0.14

Ð°Ð½ÑĮ

0.14

ç¢¼

0.13

onet

0.13

Ple

0.13

.tif

0.13

ìĩ

0.13

Activations Density 0.160%

references to interviews and conversations about films and their creators

No Comments

No Known Activations