INDEX

Explanations

historical references and notable figures in literature and philosophy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

inger

-0.18

-0.17

iment

-0.15

 Kaiser

-0.15

wend

-0.14

 Trafford

-0.14

 Hindered

-0.14

anou

-0.14

INGER

-0.14

 misuse

-0.13

POSITIVE LOGITS

 Enlightenment

0.18

SION

0.17

eenth

0.17

0.15

ayi

0.15

.nl

0.15

GI

0.14

Ukr

0.14

Activations Density 0.189%

historical references and notable figures in literature and philosophy

No Comments

No Known Activations