INDEX

Explanations

references to investigations and inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

iets

-0.17

iedade

-0.17

ality

-0.16

à¹Ĥà¸¡

-0.15

roc

-0.15

ities

-0.15

inder

-0.15

itter

-0.15

ond

-0.15

tere

-0.14

POSITIVE LOGITS

 into

0.25

 Into

0.24

into

0.21

ors

0.20

 INTO

0.20

_into

0.19

es

0.17

Into

0.17

ES

0.17

ogue

0.16

Activations Density 0.024%

references to investigations and inquiries

No Comments

No Known Activations