INDEX

Explanations

specific months and dates

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

å°

-0.17

 Vers

-0.16

mock

-0.15

aptic

-0.15

VRT

-0.15

eltas

-0.14

onis

-0.14

CCI

-0.14

itur

-0.14

arde

-0.14

POSITIVE LOGITS

adin

0.17

Ð»ÑıÐ½

0.16

adora

0.15

OTAL

0.15

engl

0.15

ģn

0.14

ument

0.14

éĽĦ

0.14

ADER

0.14

blings

0.13

Activations Density 0.023%

specific months and dates

No Comments

No Known Activations