INDEX

Explanations

code structures, such as JSON-like objects and arrays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

.infinity

-0.15

 Merrill

-0.15

isin

-0.15

lease

-0.14

enity

-0.14

icolon

-0.14

urai

-0.14

 Barney

-0.14

buie

-0.14

RITE

-0.14

POSITIVE LOGITS

amma

0.14

Ð¿ÐµÑĩ

0.14

dek

0.14

orra

0.14

atem

0.14

agas

0.14

aget

0.14

agency

0.13

CreateDate

0.13

Activations Density 0.161%

code structures, such as JSON-like objects and arrays

No Comments

No Known Activations