INDEX

Explanations

possessive forms of "is" and "be," indicating relationships or states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

gend

-0.15

Ham

-0.15

veyor

-0.15

mod

-0.15

modulo

-0.14

otton

-0.14

 print

-0.14

ham

-0.14

lt

-0.14

 Î±Ïħ

-0.14

POSITIVE LOGITS

Ð¾Ð¼Ð°

0.16

andes

0.16

.tk

0.16

ande

0.15

ades

0.15

/includes

0.14

andre

0.14

ergus

0.14

Î¬Î½Î±

0.13

vale

0.13

Activations Density 0.089%

possessive forms of "is" and "be," indicating relationships or states of being

No Comments

No Known Activations