INDEX

Explanations

references to World War I and its related military events

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

scribe

-0.15

âķĹ

-0.15

isi

-0.15

hoff

-0.14

lope

-0.14

 anymore

-0.14

OTES

-0.14

Ð»Ð°Ð³Ð¾Ð´

-0.14

ÐµÐºÑĥ

-0.14

abela

-0.13

POSITIVE LOGITS

0.15

 Pulse

0.15

ocaust

0.15

akit

0.14

ernal

0.14

idlo

0.14

ental

0.14

ernity

0.13

Activations Density 0.046%

references to World War I and its related military events

No Known Activations