INDEX

Explanations

instances of the word "like" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

subcategory

-0.15

ovah

-0.14

ÐµÐ»Ð¸Ñĩ

-0.14

sap

-0.14

AGER

-0.14

ager

-0.14

osten

-0.13

 Ð»Ð¸ÑĨ

-0.13

inja

-0.13

ucker

-0.13

POSITIVE LOGITS

usi

0.17

èµ

0.16

 butt

0.16

-minded

0.16

WISE

0.15

VERTISE

0.15

RIA

0.14

-inverse

0.14

 minded

0.14

ãĥªãĤ¢

0.14

Activations Density 0.105%

instances of the word "like" in various contexts

No Comments

No Known Activations