INDEX

Explanations

programming keywords related to 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

¼

-0.16

ADED

-0.15

ANDLE

-0.15

pong

-0.14

 Inch

-0.14

adden

-0.14

ERCHANT

-0.14

celik

-0.14

iros

-0.14

ldr

-0.14

POSITIVE LOGITS

ipple

0.17

jen

0.17

ica

0.16

anga

0.15

 Hamm

0.15

CCA

0.15

 multimedia

0.14

str

0.14

cai

0.14

éŁ¿

0.14

Activations Density 0.181%

programming keywords related to functions and methods

No Comments

No Known Activations

programming keywords related to functions and methods

No Comments

No Known Activations