INDEX

Explanations

terms related to software licensing and responsibility disclaimers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ipse

-0.18

enschaft

-0.16

imson

-0.16

agna

-0.15

arella

-0.15

 Osman

-0.15

loquent

-0.15

McB

-0.15

andre

-0.14

cpy

-0.14

POSITIVE LOGITS

rÃ¡l

0.13

ÙĬÙħÙĬ

0.13

nel

0.13

young

0.13

Ð·Ð°Ð½Ð¾

0.13

 Turnbull

0.13

æĮĩæķ°

0.13

gro

0.13

Ð³Ð°Ð»Ñĸ

0.12

wald

0.12

Activations Density 0.037%

terms related to software licensing and responsibility disclaimers

No Comments

No Known Activations