INDEX

Explanations

phrases that discuss comparisons or distinctions between two or more entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

iers

-0.16

imits

-0.16

ib

-0.16

bol

-0.15

illy

-0.15

_PROTOCOL

-0.14

jours

-0.14

 Calibration

-0.13

press

-0.13

ein

-0.13

POSITIVE LOGITS

andler

0.17

isplay

0.15

enden

0.14

ewe

0.14

ERP

0.14

/xml

0.13

childs

0.13

antor

0.13

weather

0.13

afil

0.13

Activations Density 0.015%

phrases that discuss comparisons or distinctions between two or more entities

No Comments

No Known Activations