INDEX

Explanations

geographical locations and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ToWorld

-0.16

Forum

-0.16

 Gladiator

-0.15

ubb

-0.15

ossa

-0.15

 Bucc

-0.15

eliac

-0.14

Pooling

-0.14

adena

-0.14

 ratt

-0.14

POSITIVE LOGITS

eta

0.24

Bas

0.24

Tx

0.24

ertz

0.22

Bil

0.22

tx

0.21

antz

0.21

tx

0.21

itz

0.21

atz

0.21

Activations Density 0.007%

geographical locations and related terms

No Comments

No Known Activations