INDEX

Explanations

references to programming or technical errors in code

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

agal

-0.16

Hib

-0.15

cab

-0.15

erca

-0.15

/cgi

-0.15

_ESCAPE

-0.14

agli

-0.14

 Prim

-0.14

 jersey

-0.14

rosso

-0.14

POSITIVE LOGITS

 page

0.21

pup

0.18

 Puppet

0.18

 puppet

0.18

(Page

0.17

.goto

0.17

.page

0.17

 goto

0.16

page

0.16

 evaluate

0.16

Activations Density 0.003%

references to programming or technical errors in code

No Comments

No Known Activations