INDEX

Explanations

references to follow-up actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ð°ÑĢÐ¾Ð´

-0.16

sortable

-0.15

Ð°ÑĢÐ°ÑĤ

-0.15

RowAt

-0.15

UTERS

-0.15

anas

-0.14

orting

-0.14

åĬ¡

-0.14

utterstock

-0.14

 "-"↵

-0.14

POSITIVE LOGITS

ship

0.26

-on

0.22

hip

0.21

-up

0.20

ships

0.20

up

0.19

spot

0.18

-ups

0.18

ings

0.18

endum

0.18

Activations Density 0.005%

references to follow-up actions or events

No Comments

No Known Activations