INDEX

Explanations

names of companies and individuals involved 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

arges

-0.17

_DLL

-0.16

rosso

-0.14

 ÙħØ®Øª

-0.14

 linear

-0.14

emouth

-0.14

NAS

-0.14

elsey

-0.14

aday

-0.14

ä¿

-0.14

POSITIVE LOGITS

echan

0.16

akov

0.15

die

0.15

Vig

0.14

áº±

0.14

Âŀ

0.14

íĴ

0.14

Ott

0.13

PEG

0.13

alk

0.13

Activations Density 0.062%

names of companies and individuals involved in various contexts

No Comments

No Known Activations