INDEX

Explanations

phrases related to definitions and conventions in writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

qed

-0.16

probe

-0.15

_Params

-0.15

nab

-0.15

ersions

-0.14

allis

-0.14

uben

-0.14

usterity

-0.13

jal

-0.13

awe

-0.13

POSITIVE LOGITS

 registry

0.17

 regist

0.17

 standards

0.17

 interoper

0.16

 content

0.15

 dere

0.15

iana

0.15

 resolver

0.15

 mand

0.15

URI

0.15

Activations Density 0.000%

phrases related to definitions and conventions in writing

No Comments

No Known Activations