INDEX

Explanations

conversational exchanges and expressions of understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ProcessEvent

-0.14

 ÏħÏĢÏĮ

-0.13

aan

-0.13

 humble

-0.13

Uh

-0.13

eus

-0.13

vre

-0.13

Gio

-0.13

infeld

-0.13

iver

-0.13

POSITIVE LOGITS

Ð¾ÑģÑĤÐ¸

0.16

alian

0.16

unny

0.14

ÑıÑĤ

0.14

lage

0.14

radan

0.14

 Settlement

0.14

ienen

0.14

.should

0.14

áº£o

0.13

Activations Density 0.240%

conversational exchanges and expressions of understanding

No Comments

No Known Activations