INDEX

Explanations

concepts related to self-discipline and personal well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

(æľ¨

-0.15

 outlier

-0.15

angelo

-0.14

hardt

-0.13

ARB

-0.13

OLON

-0.13

 signature

-0.13

ÙĨØ§Ø¡

-0.13

eker

-0.13

âĢĮØ³ÛĮ

-0.13

POSITIVE LOGITS

ÙģÙĩ

0.16

auc

0.15

idal

0.14

AUSE

0.14

arine

0.14

urement

0.13

Ahead

0.13

.fs

0.13

WEBPACK

0.13

 Bapt

0.13

Activations Density 0.002%

concepts related to self-discipline and personal well-being

No Comments

No Known Activations