INDEX

Explanations

numbers or numeric references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

undle

-0.16

inar

-0.15

istros

-0.14

inati

-0.14

inars

-0.14

anes

-0.14

 thing

-0.14

plode

-0.14

anki

-0.14

POSITIVE LOGITS

ikel

0.16

ickness

0.15

/md

0.14

oppel

0.14

MD

0.14

Intent

0.14

Ŀ

0.14

bid

0.14

Äįin

0.13

 SÃ¼r

0.13

Activations Density 0.068%

numbers or numeric references

No Comments

No Known Activations