INDEX

Explanations

instances of the word "great" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

omid

-0.17

pir

-0.15

itol

-0.15

mal

-0.14

yal

-0.14

ãģ¡ãĤī

-0.14

ounter

-0.13

ãĥ©ãĥ³ãĥī

-0.13

 Warren

-0.13

 dwarf

-0.13

POSITIVE LOGITS

@}

0.18

-grand

0.15

(~(

0.14

wake

0.14

defer

0.14

caret

0.14

afia

0.13

âĢĮØ³ÛĮ

0.13

ensibly

0.13

 Dá»¯

0.13

Activations Density 0.055%

instances of the word "great" and its variations

No Comments

No Known Activations