INDEX

Explanations

references to the USA 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ium

-0.17

gem

-0.15

ëįķ

-0.15

poon

-0.14

eden

-0.14

opyright

-0.14

 åĢ

-0.14

gÄ±

-0.14

ipeg

-0.14

AMILY

-0.13

POSITIVE LOGITS

etrics

0.19

SCII

0.15

ermann

0.14

 Chance

0.14

 chance

0.14

iesel

0.14

ÑĢÐ°Ð±Ð¾ÑĤ

0.14

ngle

0.14

Activations Density 0.017%

references to the USA in various contexts

No Comments

No Known Activations