INDEX

Explanations

references to cybersecurity incidents and technical issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

opoly

-0.16

 duplic

-0.15

 desert

-0.15

tre

-0.15

sko

-0.15

spy

-0.14

dsp

-0.14

spy

-0.14

JNI

-0.14

nger

-0.14

POSITIVE LOGITS

bot

0.31

 Distributed

0.28

bot

0.26

 denial

0.26

 distributed

0.26

distributed

0.25

DD

0.25

Bot

0.24

(bot

0.24

-DD

0.23

Activations Density 0.043%

references to cybersecurity incidents and technical issues

No Comments

No Known Activations