INDEX

Explanations

references to wars and conflicts, particularly in relation to Vietnam, Gaza, and ISIS

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

okin

-0.17

bie

-0.15

-0.14

 Reynolds

-0.14

ÏĨÏħ

-0.14

 Bachelor

-0.13

esen

-0.13

uv

-0.13

occ

-0.13

weeney

-0.13

POSITIVE LOGITS

 crisis

0.22

mites

0.20

-related

0.19

 situation

0.18

 Syndrome

0.18

-bound

0.17

War

0.17

ÄįÃŃ

0.17

 Desk

0.16

 Crisis

0.16

Activations Density 0.119%

references to wars and conflicts, particularly in relation to Vietnam, Gaza, and ISIS

No Comments

No Known Activations