INDEX

Explanations

instances of the word "to" indicating intention or actions

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

éĽĦ

-0.16

FO

-0.16

 Foley

-0.15

broadcast

-0.15

yne

-0.15

eder

-0.15

 Stan

-0.14

 ÑĢÐ°ÑģÐº

-0.14

ona

-0.14

ons

-0.14

POSITIVE LOGITS

iled

0.15

Statistics

0.15

ocos

0.15

bsd

0.14

ÑĢÐ°Ð±Ð¾ÑĤ

0.14

lass

0.14

 Statistics

0.14

ëĵł

0.14

Prov

0.14

OTAL

0.14

Activations Density 0.018%

instances of the word "to" indicating intention or actions

No Comments

No Known Activations