INDEX

Explanations

elements related to boundaries or transitions in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

bum

-0.19

Ð°Ð»Ð¸Ð·Ð¸

-0.15

iaux

-0.15

ØŃØ¯

-0.14

icode

-0.14

ucer

-0.14

pus

-0.13

ukt

-0.13

FIELDS

-0.13

rix

-0.13

POSITIVE LOGITS

ara

0.14

 Bannon

0.14

ìĨĮ

0.13

oloj

0.13

 æ£

0.13

 Orientation

0.13

 Bast

0.13

çµ¶

0.13

 Troy

0.13

Activations Density 0.004%

elements related to boundaries or transitions in narratives

No Comments

No Known Activations