INDEX

Explanations

conjunctions and prepositions, indicating relationships or connections

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

vÃ¡

-0.16

Rig

-0.15

 Caul

-0.15

endor

-0.15

íĮ

-0.15

asca

-0.14

lander

-0.14

Ø°Ø±

-0.14

AME

-0.14

ÑĪÐºÑĥ

-0.14

POSITIVE LOGITS

aram

0.17

ÑĨÐ¾

0.16

illis

0.15

(strpos

0.15

ÑħÐ¸

0.15

ÅĤÄħ

0.14

à¸ģà¸£à¸¡

0.14

ARAM

0.14

rzy

0.14

WC

0.13

Activations Density 0.004%

conjunctions and prepositions, indicating relationships or connections

No Comments

No Known Activations