INDEX

Explanations

references to notable historical figures and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Č↵

-0.16

'options

-0.15

aben

-0.15

ewitness

-0.14

Î²Î±

-0.14

fak

-0.14

Ø¶Ø©

-0.14

iswa

-0.13

ouro

-0.13

icio

-0.13

POSITIVE LOGITS

laz

0.16

arrison

0.15

ients

0.14

veis

0.14

otts

0.14

inea

0.14

pre

0.14

/parser

0.14

 proven

0.13

Activations Density 0.196%

references to notable historical figures and their actions

No Comments

No Known Activations