INDEX

Explanations

code related to adding or removing elements in a document structure

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

werk

-0.16

cp

-0.15

thy

-0.15

nap

-0.15

beck

-0.15

otts

-0.14

 paint

-0.14

dot

-0.14

ock

-0.14

--

-0.14

POSITIVE LOGITS

ucer

0.17

ILA

0.15

((-

0.15

èµĸ

0.15

NetMessage

0.15

ERNEL

0.14

ISCO

0.14

evin

0.14

liste

0.14

ÙĬÙĦØ§

0.14

Activations Density 0.013%

code related to adding or removing elements in a document structure

No Comments

No Known Activations