INDEX

Explanations

function definitions and control structures typically found 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 @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ãĥŃãĥ¼

-0.17

ãĥªãĥ³

-0.16

ivas

-0.16

ildren

-0.15

.ObjectId

-0.15

Gam

-0.14

.SIG

-0.14

uien

-0.14

dater

-0.14

ween

-0.14

POSITIVE LOGITS

agh

0.15

apia

0.15

 Busy

0.14

gars

0.14

otre

0.14

Zub

0.14

orer

0.13

Ø§ÙģØª

0.13

bih

0.13

Chi

0.13

Activations Density 0.268%

function definitions and control structures typically found in programming code

No Comments

No Known Activations