INDEX

Explanations

significant numbers or data points related to film and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

fix

-0.17

ixin

-0.16

 Conc

-0.14

yme

-0.14

unf

-0.14

å·

-0.13

rat

-0.13

fix

-0.13

IME

-0.13

POSITIVE LOGITS

 çģ

0.16

ancia

0.15

aling

0.14

Ã¢k

0.14

apollo

0.14

linger

0.14

çģ

0.14

metatable

0.14

 pione

0.14

è¿Ļä¸Ģ

0.13

Activations Density 0.024%

significant numbers or data points related to film and media

No Comments

No Known Activations