INDEX

Explanations

terms related to historical and architectural significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

eya

-0.14

 Tech

-0.14

 Parallel

-0.14

hev

-0.14

acie

-0.14

.gov

-0.14

lia

-0.14

acz

-0.14

gov

-0.14

thers

-0.14

POSITIVE LOGITS

HasKey

0.15

ogenic

0.14

formula

0.14

patial

0.14

rtle

0.14

indrome

0.13

Ð°Ð»ÑĸÐ²

0.13

ãĥ¼ãĥĢ

0.13

alnum

0.13

Activations Density 0.003%

terms related to historical and architectural significance

No Comments

No Known Activations