INDEX

Explanations

dimensions and measurements of objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ulton

-0.16

ardy

-0.15

afia

-0.14

à¸£à¸°à¹Ģà¸ļ

-0.14

 dostan

-0.14

rzy

-0.14

kt

-0.13

Cul

-0.13

AZY

-0.13

UDA

-0.13

POSITIVE LOGITS

cm

0.72

cm

0.68

cms

0.57

 cent

0.56

CM

0.56

cms

0.55

(cm

0.54

.cm

0.54

CM

0.52

_cm

0.51

Activations Density 0.039%

dimensions and measurements of objects

No Comments

No Known Activations