INDEX

Explanations

terms related to peace and conflict resolution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

oeff

-0.16

ndon

-0.15

.Fail

-0.14

lus

-0.14

à¸Ļà¸²à¸Ļ

-0.14

à¸Ļà¸ķ

-0.14

ekyll

-0.14

recision

-0.14

à¸¡à¸ķ

-0.14

reib

-0.14

POSITIVE LOGITS

ably

0.20

viar

0.15

fully

0.15

fulness

0.14

 Peace

0.14

DCALL

0.14

weigh

0.14

 peace

0.14

ific

0.13

ASM

0.13

Activations Density 0.023%

terms related to peace and conflict resolution

No Comments

No Known Activations