INDEX

Explanations

names and terms associated with specific locations and organizations

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

AMI

-0.15

rb

-0.15

 schedule

-0.14

anny

-0.14

 Hull

-0.14

 midterm

-0.13

ãĥ¼ãĥ©

-0.13

ru

-0.13

rc

-0.13

POSITIVE LOGITS

/Peak

0.17

 Crisis

0.15

Insn

0.15

Ú¯Ø§ÙĨ

0.15

 queryInterface

0.15

Éµ

0.15

à¹ĳ

0.15

arium

0.14

Rpc

0.14

URLException

0.14

Activations Density 0.129%

names and terms associated with specific locations and organizations

No Comments

No Known Activations