INDEX

Explanations

instances of the word "to" and its various forms in different contexts

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

ynet

-0.17

CLR

-0.15

esis

-0.15

ALSE

-0.14

estar

-0.14

THR

-0.14

agas

-0.14

Regressor

-0.14

 Harr

-0.13

ahi

-0.13

POSITIVE LOGITS

ãĥ¼ãĥª

0.15

æĪĴ

0.15

tej

0.15

aben

0.14

ì¹ľ

0.14

 somebody

0.13

 pent

0.13

 äº¬

0.13

Activations Density 0.083%

instances of the word "to" and its various forms in different contexts

No Comments

No Known Activations