INDEX

Explanations

references to sports-related moral lessons or warnings about behavior

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

ï¼Īå¹³æĪĲ

-0.16

 Kendrick

-0.15

 localization

-0.15

addon

-0.14

ustin

-0.14

alf

-0.14

Ð¶Ðµ

-0.14

ANCES

-0.14

inces

-0.14

dds

-0.14

POSITIVE LOGITS

 Connie

0.23

 Brooklyn

0.22

 Babe

0.20

 Giants

0.19

 penn

0.18

 Negro

0.18

 Browns

0.17

 barn

0.17

 Depression

0.17

ump

0.17

Activations Density 0.041%

references to sports-related moral lessons or warnings about behavior

No Comments

No Known Activations