INDEX

Explanations

references to abstract ideas or themes in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iÄħ

-0.17

 conserv

-0.17

piler

-0.16

 contents

-0.14

contents

-0.14

.minecraftforge

-0.14

ä¾ĭ

-0.14

Ã¡Å¡

-0.14

 concession

-0.14

('__

-0.14

POSITIVE LOGITS

ually

0.16

chine

0.16

ernal

0.15

Ìī

0.14

ilst

0.14

Ãµes

0.14

Spo

0.14

NAL

0.13

ebra

0.13

 Aires

0.13

Activations Density 0.019%

references to abstract ideas or themes in a variety of contexts

No Comments

No Known Activations