INDEX

Explanations

phrases indicating collaboration or similarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ãĥĥãĤ«ãĥ¼

-0.16

 '..',

-0.15

averse

-0.15

.VK

-0.14

whereIn

-0.14

ntl

-0.14

inheritDoc

-0.14

Īĺ

-0.14

URLException

-0.13

PasswordEncoder

-0.13

POSITIVE LOGITS

ensch

0.16

ãĤĪãģ³

0.15

kah

0.15

ILTER

0.15

chÃ©

0.15

IndexPath

0.14

orta

0.14

 plus

0.13

/datatables

0.13

Activations Density 0.066%

phrases indicating collaboration or similarity

No Comments

No Known Activations