INDEX

Explanations

dimensions and measurements related to physical objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

onis

-0.17

ãĥ¬ãĥ³

-0.15

áº£n

-0.15

(çģ«

-0.14

=add

-0.14

Å¡tÄĽ

-0.14

.SDK

-0.14

buie

-0.13

ÏģÏĮ

-0.13

ÙĩÙĨ

-0.13

POSITIVE LOGITS

endor

0.16

Î»Ïī

0.15

erez

0.15

 blow

0.15

arih

0.14

ossa

0.14

Loading

0.14

ihat

0.14

krom

0.14

Activations Density 0.333%

dimensions and measurements related to physical objects

No Comments

No Known Activations