INDEX

Explanations

references to philosophical concepts and practices related to self-discipline and mastery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ahoo

-0.15

eturn

-0.15

dera

-0.14

BOARD

-0.14

(er

-0.14

iÅ¾

-0.14

hurst

-0.14

 Tight

-0.14

ilateral

-0.13

 standalone

-0.13

POSITIVE LOGITS

 statically

0.14

èĥ

0.14

/stdc

0.14

ÄĻk

0.14

ÙĪÙĨÙĬØ©

0.14

Injector

0.14

atti

0.14

ahren

0.14

oton

0.13

ogui

0.13

Activations Density 2.185%

references to philosophical concepts and practices related to self-discipline and mastery

No Comments

No Known Activations