INDEX

Explanations

references to data types and memory management in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ctor

-0.16

uintptr

-0.16

vla

-0.16

 prop

-0.15

-0.14

 true

-0.14

eyh

-0.14

oard

-0.14

 prim

-0.13

levision

-0.13

POSITIVE LOGITS

yne

0.15

_kb

0.14

((!

0.14

ladu

0.14

UIG

0.14

itzer

0.14

Î³ÎµÎ¹

0.14

Mismatch

0.14

chia

0.14

loo

0.14

Activations Density 0.274%

references to data types and memory management in code

No Comments

No Known Activations