INDEX

Explanations

suggestions for locating individuals or resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

reesome

-0.18

ingu

-0.15

ypse

-0.15

ded

-0.15

rece

-0.15

Lia

-0.15

inge

-0.15

-0.14

.memo

-0.14

iske

-0.14

POSITIVE LOGITS

ìĿ´ë²Ħ

0.15

HZ

0.15

iggins

0.15

earch

0.15

 Search

0.14

 search

0.14

AFX

0.14

 pathMatch

0.14

 trom

0.14

eriod

0.14

Activations Density 0.004%

suggestions for locating individuals or resources

No Comments

No Known Activations