INDEX

Explanations

technical specifications and descriptions related to product features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

çī

-0.16

-0.15

zee

-0.15

et

-0.15

ãĥ¼ãĥķ

-0.14

avar

-0.14

apg

-0.14

Ga

-0.14

atism

-0.14

kich

-0.14

POSITIVE LOGITS

 towards

0.17

owards

0.16

tera

0.16

(Direction

0.15

odp

0.15

 Towards

0.15

 Side

0.14

 toward

0.14

 side

0.14

 ÑģÑĤÐ¾ÑĢÐ¾Ð½Ñĥ

0.14

Activations Density 0.125%

technical specifications and descriptions related to product features

No Comments

No Known Activations