INDEX

Explanations

references to exploratory missions or expeditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

omas

-0.17

orous

-0.16

kola

-0.16

xit

-0.15

XS

-0.15

 spit

-0.15

ipeg

-0.15

alus

-0.14

TEX

-0.14

POSITIVE LOGITS

airy

0.20

iment

0.20

ynos

0.19

unge

0.19

losion

0.18

(exp

0.16

lore

0.16

ary

0.16

ordinary

0.15

pci

0.15

Activations Density 0.022%

references to exploratory missions or expeditions

No Comments

No Known Activations