INDEX

Explanations

references to figures and tables within the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

mate

-0.16

ware

-0.16

etty

-0.15

.med

-0.15

.IContainer

-0.15

eness

-0.14

ename

-0.14

aid

-0.14

GINE

-0.14

 Gateway

-0.14

POSITIVE LOGITS

 below

0.16

hya

0.15

_VIRTUAL

0.14

_jobs

0.14

Interop

0.13

 Ð½Ð¸Ð¶Ðµ

0.13

kek

0.13

å°¼

0.13

 worse

0.13

 Pret

0.13

Activations Density 0.037%

references to figures and tables within the document

No Comments

No Known Activations