INDEX

Explanations

references to specific locations or communities, particularly those labeled as "village."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oron

-0.15

icker

-0.15

addock

-0.15

ervas

-0.15

.Elements

-0.14

çĽ®

-0.14

Ã²

-0.14

ibr

-0.14

oker

-0.14

icher

-0.14

POSITIVE LOGITS

gens

0.16

forman

0.15

Wid

0.15

 Copp

0.14

.SIG

0.14

reu

0.13

.external

0.13

uchs

0.13

RunWith

0.13

avia

0.13

Activations Density 0.007%

references to specific locations or communities, particularly those labeled as "village."

No Comments

No Known Activations