INDEX

Explanations

mentions of numerical values or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

otal

-0.16

oven

-0.15

ADVERTISEMENT

-0.14

ekl

-0.14

ksi

-0.14

iei

-0.13

Ð¾ÑģÑĮ

-0.13

ots

-0.13

.GetBytes

-0.13

MARY

-0.13

POSITIVE LOGITS

WithPath

0.15

atorium

0.15

 apro

0.15

estone

0.15

bom

0.14

Ã¼nd

0.14

æĺĮ

0.14

 unwrap

0.14

obot

0.13

avage

0.13

Activations Density 0.008%

mentions of numerical values or quantities

No Comments

No Known Activations