INDEX

Explanations

references to new products, services, or features

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

aname

-0.16

wf

-0.15

uft

-0.15

naz

-0.14

bjerg

-0.14

otch

-0.14

insn

-0.14

anches

-0.14

_UNDEFINED

-0.14

Âĺ

-0.14

POSITIVE LOGITS

ustral

0.16

jak

0.15

kir

0.15

uran

0.14

slot

0.14

 Svens

0.14

olle

0.14

OperationException

0.14

/apis

0.14

 Gregory

0.13

Activations Density 0.118%

references to new products, services, or features

No Comments

No Known Activations