INDEX

Explanations

terms related to software licensing and usage rights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ije

-0.16

quil

-0.15

acy

-0.15

Ã»t

-0.14

aks

-0.14

yne

-0.14

ion

-0.14

atron

-0.14

 Down

-0.14

-down

-0.14

POSITIVE LOGITS

ONTAL

0.16

idla

0.15

ibia

0.15

unless

0.15

arov

0.15

/cop

0.14

ogrÃ¡f

0.14

DRV

0.14

.gdx

0.14

modulo

0.14

Activations Density 0.003%

terms related to software licensing and usage rights

No Comments

No Known Activations

terms related to software licensing and usage rights

No Comments

No Known Activations