INDEX

Explanations

references to contact or communication actions

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

atcher

-0.18

ered

-0.16

áº§m

-0.15

åĩĮ

-0.14

utter

-0.14

 Commentary

-0.14

istik

-0.14

olas

-0.14

 Cutter

-0.13

ocrates

-0.13

POSITIVE LOGITS

 quick

0.26

 listen

0.23

 look

0.21

quick

0.19

 little

0.19

dek

0.19

 closer

0.18

 Quick

0.18

 peak

0.17

 browse

0.17

Activations Density 0.048%

references to contact or communication actions

No Comments

No Known Activations