INDEX

Explanations

phrases related to development and generations of products or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ungan

-0.18

ê³Ħ

-0.17

lsi

-0.16

ÐµÐºÑģÐ¸

-0.15

 Kemp

-0.15

ascus

-0.15

 genesis

-0.14

.MixedReality

-0.14

stras

-0.14

 perman

-0.13

POSITIVE LOGITS

.Logging

0.17

Forge

0.15

£¨

0.14

ÏĥÎ¼

0.14

forge

0.14

OC

0.14

 anale

0.14

PRIVATE

0.13

lech

0.13

estring

0.13

Activations Density 0.275%

phrases related to development and generations of products or concepts

No Comments

No Known Activations