INDEX

Explanations

punctuation marks and symbols, particularly colons and brackets, which usually denote references or formatting in academic texts

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

ÑĪÐºÐ°

-0.18

clave

-0.16

IODevice

-0.15

ordes

-0.15

-0.14

bill

-0.14

olume

-0.14

oid

-0.14

POSITIVE LOGITS

lik

0.16

enic

0.15

wig

0.14

 Byron

0.14

ÏĥÎºÎµ

0.14

ÙĪØ§ÙĦ

0.14

 Edwin

0.14

]]>

0.13

asu

0.13

olta

0.13

Activations Density 0.056%

punctuation marks and symbols, particularly colons and brackets, which usually denote references or formatting in academic texts

No Comments

No Known Activations