INDEX

Explanations

mathematical notation and symbols related to inequalities and set definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

oulos

-0.15

osy

-0.14

heads

-0.14

oldem

-0.13

_CI

-0.13

lint

-0.13

du

-0.13

aces

-0.13

uct

-0.13

POSITIVE LOGITS

ÑĩÐ°Ð¹

0.15

imde

0.15

etler

0.14

omore

0.14

å¿ł

0.14

ictim

0.14

_HT

0.14

arella

0.14

kker

0.14

kinson

0.14

Activations Density 0.110%

mathematical notation and symbols related to inequalities and set definitions

No Comments

No Known Activations