INDEX

Explanations

proper nouns related to locations, particularly U.S. states and cities, as well as terms related to intellectual property and literary genres

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

egie

-0.15

AZY

-0.14

roys

-0.14

/Open

-0.13

',(

-0.13

enthal

-0.13

Ã

-0.13

erna

-0.13

gratis

-0.13

ÑģÐ¾Ð»

-0.12

POSITIVE LOGITS

0.20

etc

0.17

 Wheeler

0.14

çŃī

0.13

ocument

0.13

alloc

0.13

ioc

0.13

 ÑĤÐ¾ÑīÐ¾

0.13

 McGu

0.13

 çŃī

0.13

Activations Density 0.149%

proper nouns related to locations, particularly U.S. states and cities, as well as terms related to intellectual property and literary genres

No Comments

No Known Activations