INDEX

Explanations

references to specific individuals or entities, particularly names connected to notable events or topics

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

àµįà´

-0.16

 viá»ĩc

-0.15

ëģĶ

-0.14

ude

-0.14

Zwe

-0.14

æľŁ

-0.14

ê

-0.14

tings

-0.14

Î¹

-0.13

Ø§ÙĬ

-0.13

POSITIVE LOGITS

wide

0.17

ÏĥÎ·

0.17

lÃ©

0.17

phans

0.17

naires

0.16

lies

0.15

.Restr

0.15

late

0.15

adata

0.15

ed

0.15

Activations Density 0.533%

references to specific individuals or entities, particularly names connected to notable events or topics

No Comments

No Known Activations