INDEX

Explanations

elements related to storytelling and personal narratives

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

elin

-0.15

ursday

-0.15

 spotted

-0.15

esson

-0.15

insky

-0.14

due

-0.14

ŃĲï¸ı

-0.14

ERCHANT

-0.14

fus

-0.13

POSITIVE LOGITS

/Dk

0.17

 nIndex

0.16

"":

0.15

nels

0.15

[System

0.14

avou

0.14

 Append

0.14

nap

0.14

SizePolicy

0.14

leground

0.14

Activations Density 0.133%

elements related to storytelling and personal narratives

No Comments

No Known Activations