INDEX

Explanations

elements related to nostalgia and personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

abela

-0.14

agma

-0.14

anon

-0.14

adora

-0.14

Ãłnh

-0.14

ouver

-0.14

ÑĥÐºÐ°

-0.13

annon

-0.13

hey

-0.13

ismo

-0.13

POSITIVE LOGITS

 lots

0.18

 Lots

0.15

elines

0.15

erland

0.13

 occasional

0.13

 ìĺ¥

0.13

 Sunder

0.13

STM

0.13

cue

0.13

 plenty

0.13

Activations Density 0.140%

elements related to nostalgia and personal experiences

No Comments

No Known Activations