INDEX

Explanations

mentions of the word "Han" or related aspects of the Hanuman figure 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 @ 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

lez

-0.15

nist

-0.15

ãĤ¦ãĤ©

-0.15

osaur

-0.15

bjerg

-0.15

-0.14

kov

-0.14

Ð¼ÐµÑĩ

-0.14

POSITIVE LOGITS

over

0.19

uÅ¡

0.18

lopen

0.17

 Solo

0.16

ibal

0.16

icap

0.16

ousse

0.16

ania

0.16

ãĥ¬ãĥ¼

0.16

afx

0.15

Activations Density 0.019%

mentions of the word "Han" or related aspects of the Hanuman figure in various contexts

No Comments

No Known Activations