INDEX

Explanations

historical terms and references related to societal structures and events

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

ifestyles

-0.19

ocity

-0.15

riday

-0.15

akeup

-0.14

izr

-0.14

OnInit

-0.14

perator

-0.14

 stran

-0.14

eva

-0.13

rasing

-0.13

POSITIVE LOGITS

bote

0.17

-house

0.17

0.15

aria

0.15

istes

0.14

less

0.14

olar

0.14

 Flem

0.14

 nuisance

0.14

-party

0.14

Activations Density 0.840%

historical terms and references related to societal structures and events

No Comments

No Known Activations