INDEX

Explanations

mentions of scams and fraud-related contexts

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

pread

-0.16

ipple

-0.16

undy

-0.16

.dump

-0.15

zet

-0.15

osi

-0.15

hek

-0.15

-0.14

ÐºÑĥÑģ

-0.14

kup

-0.14

POSITIVE LOGITS

 dinner

0.16

 casting

0.15

 based

0.15

ayah

0.15

 cast

0.15

atu

0.15

al

0.15

MLM

0.14

 allegedly

0.14

 Casting

0.14

Activations Density 0.247%

mentions of scams and fraud-related contexts

No Comments

No Known Activations