INDEX

Explanations

phrases and structures indicating involvement in programs, assistance, or commitments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ither

-0.15

icios

-0.15

uy

-0.14

ardy

-0.14

isu

-0.14

wahl

-0.14

 dynamic

-0.14

ca

-0.13

 themselves

-0.13

POSITIVE LOGITS

à¹Ģà¸Ĺ

0.15

itched

0.15

lav

0.14

bach

0.14

memberof

0.14

 Robin

0.14

ocide

0.14

_registered

0.14

 Sund

0.14

åĽ½äº§

0.14

Activations Density 0.225%

phrases and structures indicating involvement in programs, assistance, or commitments

No Comments

No Known Activations