INDEX

Explanations

specific addresses and location identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

oct

-0.16

Ð²Ð°Ð½Ð¸Ðµ

-0.15

ffee

-0.15

é«

-0.14

ahrain

-0.14

adt

-0.13

orks

-0.13

acket

-0.13

leans

-0.13

Oct

-0.13

POSITIVE LOGITS

 Circular

0.18

 circular

0.16

 Annunci

0.15

Â½

0.15

IDGET

0.15

outine

0.15

 Main

0.14

oleÄį

0.14

 Fortune

0.14

Circular

0.14

Activations Density 0.088%

specific addresses and location identifiers

No Comments

No Known Activations