INDEX

Explanations

proper nouns, particularly names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

pedia

-0.16

ollo

-0.15

/Gate

-0.14

ãģ¤ãģ¶

-0.14

Arthur

-0.14

 reportedly

-0.14

isque

-0.14

ê¼

-0.14

Ð°Ð½ÐºÐ°

-0.13

sworth

-0.13

POSITIVE LOGITS

 pers

0.19

yme

0.15

 osob

0.14

urt

0.14

ustain

0.14

lep

0.14

 Ð·Ð°Ð²ÐµÑĢ

0.13

.componentInstance

0.13

ensing

0.13

Activations Density 0.002%

proper nouns, particularly names of individuals

No Comments

No Known Activations