INDEX

Explanations

mathematical expressions and sequences, particularly related to process definitions and properties in a formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lov

-0.16

 Mess

-0.15

ampil

-0.15

abar

-0.15

mess

-0.15

itzer

-0.15

 Caul

-0.14

oom

-0.14

voj

-0.14

iro

-0.14

POSITIVE LOGITS

gin

0.17

bread

0.17

InputBorder

0.15

ÙĪØ³ÛĮ

0.15

RICT

0.15

ImageContext

0.15

 Plate

0.14

è³Ģ

0.14

onian

0.14

ÐµÑĢÐ¿

0.14

Activations Density 0.113%

mathematical expressions and sequences, particularly related to process definitions and properties in a formal context

No Comments

No Known Activations