INDEX

Explanations

discussions about personal accountability and the motivations behind actions

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

Ø¯Ø©

-0.17

ApiClient

-0.16

eza

-0.16

ÅŁt

-0.15

unga

-0.15

¦¬

-0.15

nila

-0.15

Ú¯Ø§Ø¨

-0.14

FRING

-0.14

POSITIVE LOGITS

 Harr

0.17

bit

0.16

AD

0.14

apers

0.14

 resp

0.14

omb

0.14

ite

0.13

 descr

0.13

enth

0.13

 therefore

0.13

Activations Density 0.268%

discussions about personal accountability and the motivations behind actions

No Comments

No Known Activations