INDEX

Explanations

instances of the word "si" and specific recurring phrases or structural elements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 otherwise

-0.17

urious

-0.16

Ab

-0.15

otherwise

-0.14

ÃŃÅĻ

-0.14

enticator

-0.14

 HuffPost

-0.14

ëĳ¥

-0.14

edic

-0.14

 Otherwise

-0.13

POSITIVE LOGITS

 Leonard

0.18

opsis

0.16

Ã½t

0.15

OPSIS

0.15

AVL

0.14

anca

0.14

Frameworks

0.14

orz

0.14

æ§

0.14

_chip

0.13

Activations Density 0.007%

instances of the word "si" and specific recurring phrases or structural elements in various contexts

No Comments

No Known Activations