INDEX

Explanations

code snippets and programming-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

uden

-0.15

DBG

-0.14

á»Ŀ

-0.13

ÑģÑıÑĤ

-0.13

andon

-0.13

èĿ

-0.13

å¼

-0.13

ament

-0.13

ker

-0.13

-desktop

-0.13

POSITIVE LOGITS

cÃ¼

0.18

atat

0.16

ModelProperty

0.15

lias

0.14

nothrow

0.13

equalTo

0.13

ãĤ§

0.13

uish

0.13

estone

0.13

rieben

0.13

Activations Density 0.248%

code snippets and programming-related terms

No Comments

No Known Activations