INDEX

Explanations

references to significant outcomes, support, progress, and development in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

gh

-0.17

immel

-0.17

ed

-0.16

ifen

-0.15

net

-0.14

lio

-0.14

CodeGen

-0.14

elin

-0.14

 Underground

-0.14

POSITIVE LOGITS

appable

0.18

Normalization

0.16

ipple

0.16

inalg

0.15

parsers

0.15

Ú¯Ø§ÙĨ

0.14

oins

0.14

/problems

0.14

sizei

0.14

à¤¾à¤¯à¤²

0.14

Activations Density 0.078%

references to significant outcomes, support, progress, and development in various contexts

No Comments

No Known Activations