INDEX

Explanations

terms related to business operations and announcements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

loth

-0.16

ibur

-0.14

oller

-0.14

 Barrett

-0.14

wei

-0.14

Lig

-0.14

anca

-0.13

 Lesser

-0.13

vens

-0.13

rouch

-0.13

POSITIVE LOGITS

LC

0.14

_GAP

0.14

 Coalition

0.14

 Rank

0.14

0.13

leftright

0.13

tility

0.13

ison

0.13

lc

0.13

Activations Density 0.046%

terms related to business operations and announcements

No Comments

No Known Activations