INDEX

Explanations

elements related to user attributes and statuses in a data structure or API context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Thunk

-0.17

oyo

-0.17

áº¹

-0.16

 Hansen

-0.16

aversal

-0.15

aise

-0.15

ayo

-0.15

_uart

-0.15

azel

-0.14

emale

-0.14

POSITIVE LOGITS

adar

0.16

iyim

0.14

Ã¤ll

0.14

æĦıè¯Ĩ

0.14

ziel

0.14

ëĪ

0.14

sein

0.14

eer

0.13

 folding

0.13

(rawValue

0.13

Activations Density 0.079%

elements related to user attributes and statuses in a data structure or API context

No Comments

No Known Activations

elements related to user attributes and statuses in a data structure or API context

No Comments

No Known Activations