INDEX

Explanations

references to the United States and its geopolitical interactions or influences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-0.27

-0.24

nbsp

-0.20

-0.16

edy

-0.15

nia

-0.15

Info

-0.15

rl

-0.15

ISR

-0.15

POSITIVE LOGITS

gly

0.21

.S

0.19

å®Ļ

0.17

esco

0.17

ikit

0.16

DV

0.15

ropoda

0.15

ndef

0.15

iversit

0.15

desk

0.15

Activations Density 0.056%

references to the United States and its geopolitical interactions or influences

No Comments

No Known Activations