INDEX

Explanations

phrases that indicate a narrative or storytelling structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

EG

-0.17

 Alto

-0.15

lings

-0.15

ach

-0.15

ench

-0.14

ÐµÐ³Ð¾ÑĢ

-0.14

uros

-0.14

ongs

-0.14

agh

-0.14

POSITIVE LOGITS

Dit

0.19

ifton

0.18

äº¦

0.16

kest

0.15

 Burgess

0.15

nor

0.14

dit

0.14

lehem

0.14

rech

0.14

ä¹Ł

0.14

Activations Density 0.307%

phrases that indicate a narrative or storytelling structure

No Comments

No Known Activations