INDEX

Explanations

references to government officials and political leaders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lap

-0.15

wand

-0.15

Ã¤n

-0.15

 independence

-0.14

FINITY

-0.14

eland

-0.14

nu

-0.14

amat

-0.14

alling

-0.14

POSITIVE LOGITS

acen

0.18

inic

0.15

_ie

0.15

bote

0.15

endon

0.15

Ð¸Ð½Ð¾Ðº

0.15

 legis

0.15

InnerText

0.15

æ

0.15

intree

0.15

Activations Density 0.048%

references to government officials and political leaders

No Comments

No Known Activations