INDEX

Explanations

references to research topics and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

linger

-0.17

imos

-0.16

dek

-0.15

cker

-0.15

cuts

-0.14

Ð¾Ð±ÑĢÐ°Ð·

-0.14

amus

-0.13

.Unity

-0.13

encing

-0.13

eous

-0.13

POSITIVE LOGITS

 called

0.16

 entitled

0.15

loi

0.14

called

0.14

 titled

0.14

æĹ

0.14

ocale

0.14

ampa

0.13

 corner

0.13

akeup

0.13

Activations Density 0.156%

references to research topics and publications

No Comments

No Known Activations