INDEX

Explanations

references to scientific measurements and data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ighton

-0.17

amburger

-0.17

oÅĻ

-0.15

/XMLSchema

-0.14

ï»¿↵↵

-0.14

hek

-0.14

uais

-0.14

ovit

-0.14

ï¼Ĵ

-0.14

ohen

-0.14

POSITIVE LOGITS

0.21

Ã¡t

0.15

son

0.14

ruk

0.14

ra

0.14

orn

0.14

frauen

0.14

by

0.14

Û°

0.14

Activations Density 0.098%

references to scientific measurements and data

No Comments

No Known Activations