INDEX

Explanations

expressions of inquiry or prompting for further action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Statics

-0.17

eselect

-0.16

irket

-0.16

mock

-0.16

leared

-0.16

nout

-0.16

retty

-0.15

ayed

-0.15

etri

-0.15

adden

-0.15

POSITIVE LOGITS

aisal

0.15

vat

0.15

 Pert

0.14

 sint

0.14

cas

0.14

 terra

0.14

Apt

0.13

stand

0.13

&T

0.13

AGES

0.13

Activations Density 0.015%

expressions of inquiry or prompting for further action

No Comments

No Known Activations