INDEX

Explanations

keywords or phrases related to films or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

fÃ¼g

-0.15

eru

-0.15

å¢¨

-0.15

Hud

-0.14

Ø´Ø¨

-0.14

anzi

-0.14

hed

-0.14

 Xiao

-0.14

 FindObjectOfType

-0.14

isko

-0.14

POSITIVE LOGITS

 eleg

0.14

 vert

0.14

_UNIQUE

0.14

tep

0.13

 Mant

0.13

 Modal

0.13

_markup

0.13

how

0.13

sch

0.13

 Stre

0.13

Activations Density 0.032%

keywords or phrases related to films or narratives

No Comments

No Known Activations

keywords or phrases related to films or narratives

No Comments

No Known Activations