INDEX

Explanations

references to webinars and online learning events

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aten

-0.16

erral

-0.15

 Watkins

-0.15

Ð¾Ð»Ñİ

-0.15

iro

-0.15

pla

-0.14

unda

-0.14

oin

-0.14

 Feedback

-0.13

iar

-0.13

POSITIVE LOGITS

Multiplicity

0.16

irie

0.15

 ç¨ĭ

0.15

ç¨ĭ

0.15

utz

0.14

ãģ°

0.14

otti

0.14

wiÄħ

0.14

aho

0.14

aÄŁ

0.14

Activations Density 0.004%

references to webinars and online learning events

No Comments

No Known Activations