INDEX

Explanations

instances of the word "discover" along with phrases indicating exploration or finding new things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ansom

-0.19

enden

-0.15

gers

-0.15

pel

-0.15

uate

-0.14

birds

-0.14

ronics

-0.14

ele

-0.14

ker

-0.14

owns

-0.14

POSITIVE LOGITS

0.15

iÃŁ

0.14

Ð¾Ð·Ð¼Ð¾Ð¶

0.14

IMPLEMENT

0.14

sole

0.14

æĿ¥ãģŁ

0.14

DidLoad

0.13

Touches

0.13

å¼Ł

0.13

oku

0.13

Activations Density 0.011%

instances of the word "discover" along with phrases indicating exploration or finding new things

No Comments

No Known Activations