INDEX

Explanations

personal reflections and expressions of effort or intention

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

Ì§

-0.18

ennent

-0.16

rong

-0.16

 totiÅ¾

-0.16

ilver

-0.15

ãĥ³ãĥĲ

-0.15

åĽłä¸º

-0.15

?url

-0.14

aign

-0.14

vos

-0.14

POSITIVE LOGITS

ogan

0.16

ìĿ¸ì§Ģ

0.15

-called

0.15

_WAKE

0.15

oth

0.14

leyin

0.14

eren

0.14

oner

0.14

onen

0.14

 Ulus

0.14

Activations Density 0.146%

personal reflections and expressions of effort or intention

No Comments

No Known Activations