INDEX

Explanations

conjunctions indicating relationships or connections within sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 strict

-0.18

lica

-0.17

cona

-0.16

strict

-0.15

ica

-0.15

 liberal

-0.15

mina

-0.15

ourg

-0.14

 Strict

-0.14

 STRICT

-0.14

POSITIVE LOGITS

astically

0.23

ensely

0.19

aneously

0.18

ensively

0.17

Ð°Ð»ÑĮÐ½Ð¾

0.17

 trib

0.16

ynchronously

0.16

ÄįnÄĽ

0.16

ably

0.16

avÄĽ

0.16

Activations Density 0.098%

conjunctions indicating relationships or connections within sentences

No Comments

No Known Activations