INDEX

Explanations

instances of the word "in" within 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

aldo

-0.16

stin

-0.16

ãĥ³ãĥģ

-0.15

incinn

-0.15

 Turnbull

-0.14

/copyleft

-0.14

insky

-0.14

onas

-0.14

ssi

-0.14

åħ´

-0.14

POSITIVE LOGITS

 Gang

0.15

vocab

0.14

Mob

0.14

 Clem

0.14

 Alman

0.14

ul

0.14

 gang

0.14

abs

0.14

imen

0.13

 Rent

0.13

Activations Density 0.020%

instances of the word "in" within various contexts

No Comments

No Known Activations