INDEX

Explanations

annotations related to code documentation and metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ncia

-0.15

urd

-0.15

-striped

-0.14

chop

-0.14

 Stripe

-0.14

iban

-0.14

iframe

-0.13

 popularity

-0.13

acin

-0.13

POSITIVE LOGITS

0.16

bab

0.14

oles

0.14

Î´Î¹

0.14

-ÑĤ

0.14

fos

0.14

 Witt

0.14

UD

0.14

EFAULT

0.14

Activations Density 0.003%

annotations related to code documentation and metadata

No Comments

No Known Activations