INDEX

Explanations

prominent names or entities associated with various subjects or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

mmo

-0.15

à¹Ĭ

-0.14

plier

-0.14

utto

-0.14

ç·ł

-0.14

udad

-0.13

ncy

-0.13

ButtonItem

-0.13

Î·ÏĤ

-0.13

yÄ±

-0.13

POSITIVE LOGITS

leigh

0.18

ed

0.17

ier

0.17

ings

0.17

side

0.17

spin

0.16

falls

0.16

cuts

0.16

edBy

0.15

bound

0.15

Activations Density 0.362%

prominent names or entities associated with various subjects or contexts

No Comments

No Known Activations