INDEX

Explanations

elements related to programming functions and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

arella

-0.17

ica

-0.17

aeper

-0.15

æķ·

-0.15

hausen

-0.15

á»ķ

-0.14

.AddColumn

-0.14

 nouve

-0.14

_ALIGNMENT

-0.14

 knobs

-0.14

POSITIVE LOGITS

getitem

0.21

ById

0.21

 specific

0.21

.lookup

0.21

 Abram

0.20

ByID

0.20

 Specific

0.20

 particular

0.18

.findById

0.18

 lookup

0.18

Activations Density 0.146%

elements related to programming functions and methods

No Comments

No Known Activations