INDEX

Explanations

keywords and phrases related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ardi

-0.15

Ìģc

-0.14

inth

-0.14

atar

-0.14

 dikke

-0.14

osta

-0.13

Ì£

-0.13

mouth

-0.13

leston

-0.13

ÑģÑĥÑĤ

-0.13

POSITIVE LOGITS

asad

0.14

aber

0.13

Î³ÎºÎ±

0.13

\param

0.13

 Bever

0.13

SAFE

0.13

 Willis

0.13

DDS

0.13

amping

0.13

Tie

0.13

Activations Density 0.017%

keywords and phrases related to programming and data structures

No Comments

No Known Activations