INDEX

Explanations

references to fraudulent activities or scams

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

bjerg

-0.16

gro

-0.15

elez

-0.14

igner

-0.14

 Sele

-0.14

 forthcoming

-0.14

HIR

-0.14

atta

-0.14

oda

-0.13

uir

-0.13

POSITIVE LOGITS

 promising

0.18

tun

0.17

 paras

0.16

 wollen

0.15

 promises

0.15

duk

0.15

 prom

0.15

jer

0.14

è°

0.14

ych

0.14

Activations Density 0.112%

references to fraudulent activities or scams

No Comments

No Known Activations