INDEX

Explanations

technical terms and references related to software or coding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Wert

-0.14

ough

-0.14

ek

-0.14

akt

-0.13

isman

-0.13

Scope

-0.13

abbage

-0.13

IEL

-0.13

ense

-0.13

TAIL

-0.13

POSITIVE LOGITS

oca

0.18

 Mand

0.16

itar

0.16

-scalable

0.15

.getOwnPropertyDescriptor

0.15

Ð½Ð°Ð´Ð»ÐµÐ¶

0.15

luÅ¾

0.15

orget

0.15

EMON

0.15

nowledge

0.15

Activations Density 0.023%

technical terms and references related to software or coding

No Comments

No Known Activations