INDEX

Explanations

statements about existence or conditions of objects or concepts, often focusing on their characteristics or statuses

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

ä¸ĺ

-0.16

eus

-0.15

esine

-0.14

ahlen

-0.14

_SD

-0.14

è¾ħ

-0.13

quant

-0.13

aÅ¼

-0.13

eu

-0.13

VD

-0.13

POSITIVE LOGITS

 fine

0.23

fine

0.19

 documented

0.18

 Fine

0.17

 kind

0.17

 covered

0.17

oko

0.16

 discouraged

0.16

 handled

0.16

 legacy

0.16

Activations Density 0.251%

statements about existence or conditions of objects or concepts, often focusing on their characteristics or statuses

No Comments

No Known Activations