INDEX

Explanations

mentions of the name "Beethoven."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

fy

-0.16

.pe

-0.15

fen

-0.15

ons

-0.14

hol

-0.14

rik

-0.14

ager

-0.14

ss

-0.14

 Hollow

-0.14

POSITIVE LOGITS

atrix

0.23

auf

0.21

ijing

0.19

(Be

0.19

ahan

0.19

aud

0.17

Ð¾Ð³ÑĢÐ°Ð´

0.17

 sure

0.17

auce

0.17

ethoven

0.16

Activations Density 0.030%

mentions of the name "Beethoven."

No Comments

No Known Activations