INDEX

Explanations

plans and frameworks related to design and organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ÅĽcie

-0.17

 Ð²ÐµÐ´

-0.15

Yas

-0.14

ÑĢÐ°Ð¿

-0.14

enberg

-0.14

election

-0.13

ounce

-0.13

HING

-0.13

ipt

-0.13

Ã©lÃ©

-0.13

POSITIVE LOGITS

udden

0.17

@Id

0.15

raig

0.15

labs

0.14

.bunifuFlatButton

0.14

Ã¼gen

0.14

nav

0.14

okes

0.14

ãĥĬãĥ¼

0.13

cps

0.13

Activations Density 0.037%

plans and frameworks related to design and organization

No Comments

No Known Activations