INDEX

Explanations

geographical features and elevations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Mountains

-0.38

 mountains

-0.36

 mountain

-0.35

 hills

-0.33

 hill

-0.32

Mountain

-0.30

 Mountain

-0.29

å±±

-0.29

mount

-0.29

Mount

-0.26

POSITIVE LOGITS

annes

0.15

 Maur

0.15

fld

0.15

 Moran

0.14

pray

0.14

 Prob

0.14

icago

0.14

ailles

0.14

fir

0.14

fila

0.14

Activations Density 0.024%

geographical features and elevations

No Comments

No Known Activations