INDEX

Explanations

phrases indicating the concept of a 'book' and its various attributes or contexts

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

ALLED

-0.14

 Monroe

-0.14

avel

-0.14

affles

-0.14

Attachment

-0.13

erm

-0.13

Semantic

-0.13

ÐµÑĢÐµ

-0.13

aget

-0.13

inston

-0.13

POSITIVE LOGITS

/compiler

0.19

ingo

0.17

deniz

0.15

ra

0.15

atz

0.14

perPage

0.14

 dÄ±ÅŁÄ±

0.14

ilty

0.14

Ð»Ð¾Ð¹

0.14

EqualityComparer

0.14

Activations Density 0.015%

phrases indicating the concept of a 'book' and its various attributes or contexts

No Comments

No Known Activations