INDEX

Explanations

phrases related to research findings and study results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ante

-0.16

ista

-0.15

antes

-0.15

-0.14

stell

-0.14

 aspects

-0.14

ä¹Į

-0.14

ismo

-0.14

amo

-0.14

og

-0.13

POSITIVE LOGITS

dbe

0.16

å¼¥

0.16

inely

0.16

 Shields

0.16

chwitz

0.15

aments

0.15

 Horny

0.14

APON

0.14

veis

0.14

 older

0.14

Activations Density 0.182%

phrases related to research findings and study results

No Comments

No Known Activations