INDEX

Explanations

database-related terms and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ruk

-0.14

dbus

-0.14

/tools

-0.14

rott

-0.13

ãģĴ

-0.13

inflate

-0.13

SystemService

-0.13

ÏĪÎ·

-0.13

;element

-0.13

inf

-0.13

POSITIVE LOGITS

ht

0.16

ocker

0.16

åĹ

0.15

 Circus

0.15

0.14

assin

0.14

 Comet

0.14

 Jensen

0.14

htar

0.14

Activations Density 0.012%

database-related terms and structures

No Comments

No Known Activations