INDEX

Explanations

terms related to mentorship, leadership, and stewardship roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

eyed

-0.18

ãĤ

-0.16

InView

-0.15

lemetry

-0.14

linger

-0.14

ÑĩÐµÐ¼

-0.13

 BITTE

-0.13

favor

-0.13

regon

-0.13

compressed

-0.13

POSITIVE LOGITS

ship

0.99

 ship

0.85

Ship

0.80

ships

0.78

hip

0.75

SHIP

0.75

 Ship

0.74

 ships

0.63

(ship

0.63

hips

0.61

Activations Density 0.093%

terms related to mentorship, leadership, and stewardship roles

No Comments

No Known Activations