INDEX

Explanations

phrases that indicate lists or groupings

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

 those

-0.18

those

-0.18

ntag

-0.17

rous

-0.15

ETERS

-0.15

Those

-0.15

 ÑĤÐµ

-0.15

outil

-0.15

inz

-0.15

thouse

-0.15

POSITIVE LOGITS

 days

0.19

cond

0.19

ction

0.17

esus

0.17

uns

0.16

lected

0.16

áº§m

0.16

Days

0.15

exc

0.15

Î¬Î½ÏĦÎ±

0.15

Activations Density 0.065%

phrases that indicate lists or groupings

No Comments

No Known Activations

phrases that indicate lists or groupings

No Comments

No Known Activations