INDEX

Explanations

references to origins or sources of various subjects

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

ano

-0.17

 extracted

-0.17

extract

-0.17

Extract

-0.17

 taken

-0.16

ANO

-0.16

-0.15

taken

-0.15

ano

-0.15

áº»

-0.14

POSITIVE LOGITS

 directly

0.34

direct

0.25

Direct

0.25

 DIRECT

0.24

çĽ´æİ¥

0.23

 Direct

0.23

 straight

0.22

 direct

0.22

 doÄŁrudan

0.21

 diret

0.21

Activations Density 0.068%

references to origins or sources of various subjects

No Comments

No Known Activations