INDEX

Explanations

numeric data and statistics related to user interactions and ratings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Sor

-0.17

éŃĤ

-0.16

ksi

-0.15

:animated

-0.15

á»£

-0.14

tractor

-0.14

ptic

-0.14

Rek

-0.14

sor

-0.13

 Sovere

-0.13

POSITIVE LOGITS

aine

0.20

imest

0.17

ernen

0.17

rang

0.16

ãģĨãģ¡

0.15

elines

0.15

hlas

0.15

romo

0.14

odia

0.14

iale

0.14

Activations Density 0.087%

numeric data and statistics related to user interactions and ratings

No Comments

No Known Activations