INDEX

Explanations

references to DNS records and related functional elements in code

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

dÃŃ

-0.18

éĻµ

-0.16

onda

-0.15

Probe

-0.15

pf

-0.15

ancode

-0.15

berman

-0.14

ances

-0.14

essel

-0.14

ÑĩÐµÑģÐºÐ°Ñı

-0.14

POSITIVE LOGITS

neau

0.15

rud

0.14

annon

0.14

 compt

0.14

uto

0.13

ipple

0.13

 curt

0.13

ilt

0.13

é¦

0.13

 Thoughts

0.13

Activations Density 0.037%

references to DNS records and related functional elements in code

No Comments

No Known Activations