INDEX

Explanations

proper nouns, particularly names of individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ÄĻ

-0.17

enz

-0.16

 çī

-0.15

ombok

-0.15

imin

-0.14

éħ¸

-0.14

burgh

-0.14

expo

-0.14

lesi

-0.14

 Ø§ÙĦÙħØµ

-0.14

POSITIVE LOGITS

SEQU

0.15

lek

0.14

eer

0.14

istrovstvÃŃ

0.14

 fund

0.14

 MacDonald

0.14

Ĥ¤

0.14

inions

0.14

uib

0.14

czy

0.13

Activations Density 0.043%

proper nouns, particularly names of individuals and organizations

No Comments

No Known Activations