INDEX

Explanations

references to specific brands or products related to technology and cooking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

cene

-0.17

 Minds

-0.15

ifax

-0.15

utt

-0.15

 Ø®Ø§Ø·Ø±

-0.14

cube

-0.14

ÄĽÅĻ

-0.14

agh

-0.14

 Surge

-0.14

ãģĴ

-0.14

POSITIVE LOGITS

AdapterFactory

0.15

nonnull

0.15

Â®

0.14

å¥ī

0.14

 thuáºŃt

0.14

ÙĤØ§Ùħ

0.14

 fatty

0.14

TM

0.14

aklÄ±

0.14

ÙĥØ§Ùħ

0.13

Activations Density 0.056%

references to specific brands or products related to technology and cooking

No Comments

No Known Activations