INDEX

Explanations

references to racing events and participants

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

ezi

-0.16

anker

-0.15

exus

-0.14

esson

-0.14

ÙħÙĪØ¯

-0.14

å¡

-0.14

indir

-0.14

MESS

-0.14

.ph

-0.14

erin

-0.14

POSITIVE LOGITS

Ð°ÑĩÐµ

0.17

 Partner

0.16

otonin

0.15

Hav

0.14

Kay

0.14

co

0.14

sta

0.14

 partner

0.14

 TEAM

0.14

 team

0.14

Activations Density 0.182%

references to racing events and participants

No Comments

No Known Activations