INDEX

Explanations

prominent names or surnames 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

çĶļ

-0.14

ede

-0.13

ãĤĪãģĨãģ§ãģĻ

-0.13

 premiere

-0.13

rej

-0.12

fixtures

-0.12

adele

-0.12

 Ø§ÙĦØ°ÙĬÙĨ

-0.12

 kterÃ¡

-0.12

scribe

-0.12

POSITIVE LOGITS

bio

0.21

Bio

0.20

bio

0.19

.bio

0.18

Bio

0.18

Named

0.18

 interview

0.17

 Named

0.17

 profile

0.17

 grew

0.17

Activations Density 0.222%

prominent names or surnames in various contexts

No Comments

No Known Activations