INDEX

Explanations

references to mentoring programs and guidance for students

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ÐµÐ³Ð°

-0.15

bitset

-0.14

sts

-0.14

åĬŀ

-0.14

IDS

-0.14

ergus

-0.14

[...,

-0.14

lom

-0.13

HEMA

-0.13

omnia

-0.13

POSITIVE LOGITS

 Ment

0.40

 mentor

0.39

 mentors

0.38

 ment

0.37

mentor

0.35

 mentoring

0.35

 pairing

0.34

 pair

0.34

 Pair

0.33

 matched

0.33

Activations Density 0.075%

references to mentoring programs and guidance for students

No Comments

No Known Activations