INDEX

Explanations

instances of the word "to" 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 @ 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

otte

-0.15

ÐµÑĢÐ¸Ð½

-0.14

otta

-0.14

zcze

-0.13

 Reporting

-0.13

nnen

-0.13

letcher

-0.13

 æ©

-0.13

intl

-0.13

Å¾en

-0.13

POSITIVE LOGITS

ãĥ©ãĤ¹

0.17

ilog

0.16

ricks

0.15

 Rough

0.15

alet

0.15

enticator

0.14

 pref

0.14

èĪį

0.13

 vanity

0.13

Activations Density 0.023%

instances of the word "to" in various contexts

No Comments

No Known Activations