INDEX

Explanations

phrases related to loss or negative impact affecting individuals or groups

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

Not in Any Lists

No Comments

Negative Logits

 Bibli

-0.15

asic

-0.15

sez

-0.15

#+#

-0.14

Blo

-0.14

apro

-0.14

ebi

-0.14

":"/

-0.14

byt

-0.13

ooky

-0.13

POSITIVE LOGITS

 Deng

0.17

uela

0.15

 Guerr

0.14

ë´ī

0.14

ivet

0.14

ANGER

0.14

.Symbol

0.14

dsp

0.14

abile

0.13

angers

0.13

Activations Density 0.036%

phrases related to loss or negative impact affecting individuals or groups

No Comments

No Known Activations