INDEX

Explanations

quoted or labeled phrases and statements within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

æĺŃ

-0.15

ÐºÑĥÐ»

-0.15

èŃ

-0.14

utenant

-0.13

è¦ļ

-0.13

 uncomment

-0.13

 Jako

-0.13

 Giang

-0.13

ÎĨ

-0.13

 properly

-0.12

POSITIVE LOGITS

 Danger

0.16

rafted

0.16

-caption

0.15

 Made

0.15

EXIT

0.15

 Â©

0.14

RAFT

0.14

 PROPERTY

0.14

copyright

0.14

 danger

0.14

Activations Density 0.094%

quoted or labeled phrases and statements within the text

No Comments

No Known Activations