INDEX

Explanations

concepts related to language learning and teaching strategies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 primal

-0.15

ichni

-0.14

ova

-0.14

ç®Ĺ

-0.14

ä»°

-0.14

 antioxid

-0.14

--------------------------------------------------------------------------↵

-0.14

YRO

-0.13

 fluores

-0.13

ascii

-0.13

POSITIVE LOGITS

 Habit

0.18

 correct

0.17

echn

0.15

ameleon

0.15

american

0.14

 memor

0.14

 Correct

0.14

exion

0.14

 contexts

0.14

Correct

0.14

Activations Density 0.005%

concepts related to language learning and teaching strategies

No Comments

No Known Activations