INDEX

Explanations

terms related to nourishment and replenishment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

onto

-0.16

akers

-0.15

 wearing

-0.15

ic

-0.15

ability

-0.15

ually

-0.14

ordes

-0.14

atically

-0.14

Ð°Ð½Ðµ

-0.14

plane

-0.14

POSITIVE LOGITS

ishing

0.68

ished

0.66

ishment

0.64

ish

0.60

ishes

0.54

ISH

0.50

ishments

0.48

isher

0.48

ISHED

0.47

lish

0.38

Activations Density 0.027%

terms related to nourishment and replenishment

No Comments

No Known Activations