INDEX

Explanations

references to San Diego

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

iaux

-0.16

.getLog

-0.15

idon

-0.14

 unless

-0.14

ADX

-0.14

sme

-0.14

ÄĮ

-0.14

âĺħ

-0.13

bottom

-0.13

 Presidential

-0.13

POSITIVE LOGITS

lev

0.17

emme

0.15

aren

0.15

ikat

0.15

aar

0.15

rame

0.14

asto

0.14

ÑĢÐ¾Ð¹

0.13

LINE

0.13

lines

0.13

Activations Density 0.002%

references to San Diego

No Comments

No Known Activations