INDEX

Explanations

connections and relationships between different concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

zdy

-0.18

BOVE

-0.14

AnimationFrame

-0.14

Ø±Ø¨ÛĮ

-0.14

YGON

-0.14

-mf

-0.14

ÏĦÎ¹ÎºÎ±

-0.14

IGINAL

-0.13

USTOM

-0.13

zon

-0.13

POSITIVE LOGITS

/or

0.31

ients

0.21

 optionally

0.21

 convers

0.21

0.20

 vice

0.20

 especially

0.20

 sometimes

0.19

 also

0.19

 counterpart

0.19

Activations Density 0.283%

connections and relationships between different concepts or entities

No Comments

No Known Activations