INDEX

Explanations

numerical values associated with counts and measurements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

nox

-0.14

ISCO

-0.13

afi

-0.13

ofire

-0.13

orsi

-0.13

DIRECT

-0.13

combo

-0.13

/cgi

-0.12

andi

-0.12

Klo

-0.12

POSITIVE LOGITS

 versus

0.27

vs

0.27

 ettÃ¤

0.22

-,

0.21

ãĢģä¸Ń

0.18

 láº«n

0.17

 ìķĦëĭĪëĿ¼

0.17

ãĢģ

0.15

ignet

0.15

_vs

0.15

Activations Density 0.276%

numerical values associated with counts and measurements in various contexts

No Comments

No Known Activations