INDEX

Explanations

references to research institutions and academic roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 hang

-0.15

 Hang

-0.15

 Cabin

-0.14

orpion

-0.14

 hanging

-0.14

 NavParams

-0.14

-detail

-0.14

 Insider

-0.14

Lab

-0.14

 reflux

-0.14

POSITIVE LOGITS

errer

0.15

/Dk

0.15

ãĥ³ãĥķ

0.15

dez

0.14

yne

0.14

ucu

0.14

inker

0.14

evin

0.14

riba

0.14

rsp

0.14

Activations Density 0.097%

references to research institutions and academic roles

No Comments

No Known Activations