INDEX

Explanations

references to academic journal articles and their formatting details

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

olist

-0.16

ince

-0.15

ke

-0.15

dot

-0.14

pie

-0.14

oland

-0.14

 Cust

-0.14

fill

-0.14

-0.13

iden

-0.13

POSITIVE LOGITS

ÏĥÏĩ

0.16

 treff

0.15

mada

0.15

 CLOSED

0.15

ebo

0.15

ãĥ³ãĥĨãĤ£

0.15

 Ð¿ÑĸÐ´Ñģ

0.15

_vue

0.14

 thuyáº¿t

0.14

kli

0.14

Activations Density 0.003%

references to academic journal articles and their formatting details

No Comments

No Known Activations