INDEX

Explanations

references to code and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

kah

-0.16

 zast

-0.15

oft

-0.15

izzie

-0.14

quier

-0.14

LED

-0.14

atron

-0.14

oca

-0.14

izaciÃ³n

-0.14

oyo

-0.14

POSITIVE LOGITS

ught

0.18

kr

0.16

riterion

0.15

 Peer

0.15

abcdefgh

0.14

eniable

0.14

 Watkins

0.14

ughty

0.14

rzy

0.14

Activations Density 0.276%

references to code and programming concepts

No Comments

No Known Activations