INDEX

Explanations

dates and specific events associated with them

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

kovÃ¡

-0.16

ugo

-0.16

-0.14

iez

-0.14

ç¦ıåĪ©

-0.14

inator

-0.13

Raf

-0.13

ius

-0.13

iat

-0.13

alam

-0.13

POSITIVE LOGITS

pa

0.16

oire

0.15

 Institution

0.15

_requires

0.14

ouser

0.14

_pa

0.14

ULO

0.14

anou

0.14

swire

0.14

Activations Density 0.043%

dates and specific events associated with them

No Comments

No Known Activations