INDEX

Explanations

occurrences of the word "Thorpe."

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

ãĤ¯ãĥ©ãĥĸ

-0.15

 commerc

-0.15

 ActiveForm

-0.15

 Clarkson

-0.15

ç±į

-0.14

lash

-0.14

rix

-0.14

rlen

-0.14

blick

-0.14

POSITIVE LOGITS

 kÃ¼r

0.16

sprintf

0.15

 Levi

0.14

ìķĪ

0.14

legate

0.14

 Russell

0.14

jo

0.14

íĥķ

0.13

 Pall

0.13

adj

0.13

Activations Density 0.008%

occurrences of the word "Thorpe."

No Comments

No Known Activations