INDEX

Explanations

terms related to instructional guidelines and procedures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

amburger

-0.15

BIT

-0.15

 Wikispecies

-0.15

opsis

-0.15

Digest

-0.15

 Digest

-0.15

 Revised

-0.15

Ø±Ø³ÛĮ

-0.15

inger

-0.15

aye

-0.14

POSITIVE LOGITS

¶Į

0.15

_ANDROID

0.15

 prostitut

0.15

Kin

0.15

LEE

0.15

æ®Ĭ

0.14

ê±°ëĤĺ

0.14

Kin

0.14

-alist

0.14

yles

0.13

Activations Density 0.595%

terms related to instructional guidelines and procedures

No Comments

No Known Activations