INDEX

Explanations

references to suggestions or recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Deck

-0.16

á»Ĩ

-0.15

clair

-0.15

UM

-0.14

Deck

-0.14

 deck

-0.14

obia

-0.14

affe

-0.14

IMP

-0.14

DataTask

-0.14

POSITIVE LOGITS

 above

0.30

 earlier

0.25

 previous

0.24

above

0.23

 Above

0.21

 ABOVE

0.21

 suggestion

0.20

_above

0.20

åĪļæīį

0.19

Activations Density 0.086%

references to suggestions or recommendations

No Comments

No Known Activations