INDEX

Explanations

concepts centered around self-reflection and personal growth

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

sian

-0.15

adx

-0.15

chte

-0.14

opis

-0.14

bread

-0.14

.go

-0.14

rette

-0.13

 Parties

-0.13

 cele

-0.13

cloth

-0.13

POSITIVE LOGITS

erras

0.17

 humble

0.16

lear

0.15

hum

0.15

Hum

0.15

å¼ĢæĶ¾

0.14

rana

0.14

AILS

0.14

 modest

0.14

eras

0.14

Activations Density 0.240%

concepts centered around self-reflection and personal growth

No Comments

No Known Activations