INDEX

Explanations

phrases conveying existence or location of items or concepts

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

linger

-0.19

rs

-0.18

iro

-0.15

net

-0.14

æł·

-0.14

 daylight

-0.14

amo

-0.14

AA

-0.14

adÄĽ

-0.14

 pert

-0.14

POSITIVE LOGITS

ensing

0.16

ÙĴØŃ

0.16

eken

0.16

kea

0.15

agna

0.15

ikt

0.15

Falsy

0.14

.camel

0.14

ocha

0.14

 Briggs

0.14

Activations Density 0.031%

phrases conveying existence or location of items or concepts

No Comments

No Known Activations