INDEX

Explanations

references to additional benefits or features

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

-0.16

/fw

-0.16

 Claus

-0.15

igo

-0.15

iram

-0.14

etin

-0.14

 sunday

-0.14

sburgh

-0.13

POSITIVE LOGITS

enger

0.15

fore

0.14

ieres

0.14

Neutral

0.14

uze

0.14

odal

0.14

uml

0.14

usto

0.14

BO

0.14

 whatever

0.14

Activations Density 0.011%

references to additional benefits or features

No Comments

No Known Activations