INDEX

Explanations

proper nouns, particularly names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

odont

-0.16

oly

-0.15

eacher

-0.14

goog

-0.14

ibu

-0.14

elan

-0.14

 unders

-0.14

Ð¸ÑĤÐµÐ»ÐµÐ¹

-0.14

(Of

-0.13

åĵ

-0.13

POSITIVE LOGITS

 Scott

0.18

Scott

0.16

æ¬¾

0.15

à¸¥à¸°

0.15

oval

0.14

ÎµÎ¯Î¿

0.14

 UIResponder

0.14

 máº¡i

0.14

Ð²ÐµÑĢÐ´

0.13

setScale

0.13

Activations Density 0.023%

proper nouns, particularly names and titles

No Comments

No Known Activations