INDEX

Explanations

the word "beyond" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 chung

-0.15

ãģ¾ãģ¾

-0.15

EDIA

-0.15

ritch

-0.14

zelf

-0.14

ourcem

-0.14

Ð½Ð¸Ð²

-0.14

HashTable

-0.14

ë¦¬ì¹´

-0.14

ainless

-0.14

POSITIVE LOGITS

 Beyond

0.17

Zy

0.16

 beyond

0.16

Beyond

0.16

-reaching

0.15

ria

0.14

æ¥Ń

0.14

tti

0.14

aries

0.14

Activations Density 0.016%

the word "beyond" in various contexts

No Comments

No Known Activations