INDEX

Explanations

references to scientific publications and their details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Empty

-0.15

Pur

-0.15

 Dispatcher

-0.15

arget

-0.14

 cert

-0.14

çĽ

-0.14

 æ®

-0.14

omba

-0.14

boom

-0.13

stim

-0.13

POSITIVE LOGITS

izu

0.15

.Magenta

0.15

-INF

0.15

raÅ¾

0.14

-fw

0.14

orsch

0.14

obutton

0.14

deer

0.14

spo

0.14

InstantiationException

0.14

Activations Density 0.005%

references to scientific publications and their details

No Comments

No Known Activations