INDEX

Explanations

technical terms and keywords related to programming and software systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

èĬĤ

-0.15

ppard

-0.15

 Depth

-0.14

Depth

-0.14

kem

-0.14

Lah

-0.14

 Oswald

-0.14

yny

-0.14

_DF

-0.14

finder

-0.14

POSITIVE LOGITS

odu

0.16

onta

0.16

ylon

0.15

ilen

0.14

hsi

0.14

llen

0.14

alic

0.14

race

0.14

 illeg

0.14

anvas

0.14

Activations Density 0.013%

technical terms and keywords related to programming and software systems

No Comments

No Known Activations