INDEX

Explanations

instances of the abbreviation "SIG" across various contexts

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

idge

-0.19

imo

-0.16

å§¿

-0.15

ullo

-0.15

nelle

-0.15

ody

-0.15

enger

-0.15

à¤¾à¤

-0.15

ike

-0.14

iggins

-0.14

POSITIVE LOGITS

ourney

0.29

gy

0.21

ificance

0.20

Sig

0.20

(SIG

0.19

ificantly

0.19

mund

0.18

mond

0.18

.SIG

0.18

ificant

0.17

Activations Density 0.011%

instances of the abbreviation "SIG" across various contexts

No Comments

No Known Activations