INDEX

Explanations

references to programming-related issues and errors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

lush

-0.18

jie

-0.16

leston

-0.16

AGO

-0.15

icon

-0.15

vale

-0.15

azon

-0.14

Ø§Ø´Øª

-0.14

Icon

-0.14

 Icon

-0.14

POSITIVE LOGITS

ambi

0.17

ossil

0.14

edited

0.14

(ur

0.14

lef

0.14

Î¯Ïĥ

0.13

ech

0.13

/REC

0.13

reta

0.13

 answer

0.13

Activations Density 0.015%

references to programming-related issues and errors

No Comments

No Known Activations