INDEX

Explanations

terms related to education and learning processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

NECTION

-0.14

iÅ¾

-0.14

ëıħ

-0.14

Ø§Ø¸

-0.14

igung

-0.14

ìĿ´ëĿ¼ëĬĶ

-0.13

illin

-0.13

_CFG

-0.12

IENTATION

-0.12

(glm

-0.12

POSITIVE LOGITS

 such

1.20

 like

1.03

such

0.97

 SUCH

0.83

 Such

0.80

Such

0.77

 seperti

0.74

 zoals

0.68

 nhÆ°

0.67

å¦Ĥ

0.66

Activations Density 2.059%

terms related to education and learning processes

No Comments

No Known Activations