INDEX

Explanations

indicators of growth and expansion within organizations or communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 descending

-0.15

 plummet

-0.14

swick

-0.14

 shorter

-0.14

iselect

-0.14

izr

-0.14

mtime

-0.13

WillDisappear

-0.13

kil

-0.13

POSITIVE LOGITS

 expansion

0.75

 Expansion

0.72

Expansion

0.66

 expand

0.66

 expansions

0.66

expand

0.63

æī©

0.62

 expands

0.60

 expanded

0.59

 expanding

0.59

Activations Density 0.395%

indicators of growth and expansion within organizations or communities

No Comments

No Known Activations