INDEX

Explanations

specific names and terms related to scientific or technical 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

utters

-0.16

ezi

-0.16

 Micha

-0.16

ignon

-0.15

adesh

-0.15

ayers

-0.15

tero

-0.14

Collections

-0.14

antan

-0.14

Fle

-0.13

POSITIVE LOGITS

adolu

0.15

same

0.14

nier

0.13

onse

0.13

pu

0.13

fr

0.13

enci

0.13

Bol

0.13

Ð·Ð½

0.13

obil

0.13

Activations Density 0.064%

specific names and terms related to scientific or technical concepts

No Comments

No Known Activations