INDEX

Explanations

numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ipers

-0.15

soever

-0.15

neath

-0.14

ptune

-0.14

hd

-0.14

insic

-0.14

alias

-0.14

vere

-0.14

ligt

-0.13

pez

-0.13

POSITIVE LOGITS

0.17

@$

0.16

storybook

0.15

ILLS

0.14

esModule

0.14

latest

0.14

ElementException

0.14

Î±ÏĢÏĮ

0.13

PFN

0.13

ills

0.13

Activations Density 0.136%

numerical data or statistics

No Comments

No Known Activations