INDEX

Explanations

expressions of desire or interest, particularly those paired with "love to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

umpt

-0.18

assis

-0.15

AFE

-0.15

KB

-0.14

nga

-0.14

rtle

-0.14

spd

-0.14

afe

-0.13

lite

-0.13

ls

-0.13

POSITIVE LOGITS

 nothing

0.17

 kdyby

0.17

 Nothing

0.16

Ð»Ð¸Ñħ

0.16

à¸Īà¸£

0.16

 hear

0.15

hana

0.15

 knowing

0.15

Ow

0.15

cip

0.15

Activations Density 0.028%

expressions of desire or interest, particularly those paired with "love to."

No Comments

No Known Activations