INDEX

Explanations

references to teaching, education, and instructional methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

icana

-0.15

.sourceforge

-0.15

ibling

-0.14

::-

-0.14

Ø³ØªØ§ÙĨ

-0.14

 protections

-0.13

.lift

-0.13

ÙıÙĪØ§

-0.13

ivot

-0.12

 Manufacturers

-0.12

POSITIVE LOGITS

 instruct

0.44

 teaching

0.43

 teach

0.41

 teaches

0.34

-te

0.34

 Teaching

0.33

 coaching

0.32

 instruction

0.32

 coach

0.31

 Teach

0.30

Activations Density 0.262%

references to teaching, education, and instructional methods

No Comments

No Known Activations