INDEX

Explanations

titles and descriptions related to events and presentations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

iliz

-0.15

ÏĦÎ¹ÎºÎ±

-0.15

endar

-0.15

essler

-0.14

 \↵

-0.14

EventArgs

-0.14

 Knot

-0.13

odb

-0.13

iz

-0.12

arat

-0.12

POSITIVE LOGITS

uds

0.16

æ¯

0.15

chemist

0.15

oulos

0.15

assandra

0.14

åĬª

0.14

rometer

0.14

ovna

0.13

çĶ

0.13

 chem

0.13

Activations Density 0.129%

titles and descriptions related to events and presentations in various contexts

No Comments

No Known Activations