INDEX

Explanations

instances of specific words related to familiar names or possible recognizable terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

alom

-0.15

unte

-0.15

oci

-0.15

ancell

-0.15

tanggal

-0.14

uliar

-0.14

æĽľ

-0.14

Ð»Ð°ÑģÑĤÐ¸

-0.14

 Clover

-0.14

POSITIVE LOGITS

 competitive

0.17

 Competitive

0.15

 Charg

0.15

iedy

0.15

ceptors

0.15

ibling

0.15

onn

0.15

adm

0.15

oad

0.15

 UÅ¾

0.15

Activations Density 0.023%

instances of specific words related to familiar names or possible recognizable terms

No Comments

No Known Activations