INDEX

Explanations

instances of discussions or threads that indicate a starting point in conversations

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

aroo

-0.16

/goto

-0.15

Ã³m

-0.15

 Independence

-0.14

airy

-0.14

swick

-0.14

_portal

-0.14

à¹īà¸Ńà¸Ļ

-0.14

mach

-0.14

endl

-0.14

POSITIVE LOGITS

yr

0.16

Äĥm

0.15

ContentAlignment

0.14

_deps

0.14

tains

0.14

aba

0.14

_Template

0.13

 Goodman

0.13

æĶ¯

0.13

nga

0.13

Activations Density 0.003%

instances of discussions or threads that indicate a starting point in conversations

No Comments

No Known Activations