INDEX

Explanations

structure or syntax in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÃĹ↵↵

-0.17

iken

-0.16

thane

-0.16

æ½

-0.15

incy

-0.15

UAGE

-0.15

.scalablytyped

-0.14

_REFER

-0.14

gaard

-0.14

anz

-0.14

POSITIVE LOGITS

 assert

0.85

assert

0.80

 assertion

0.71

 Assert

0.68

 asserting

0.64

Assert

0.63

	assert

0.63

 asserts

0.63

 assertions

0.63

 asserted

0.62

Activations Density 0.004%

structure or syntax in programming code

No Comments

No Known Activations