INDEX

Explanations

references to combinations or packages of products or items

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

usi

-0.16

pike

-0.15

aris

-0.15

 Ð¿ÑĢÐ¾ÑĢ

-0.14

zel

-0.14

pb

-0.14

 Mast

-0.14

å±ħ

-0.14

Ð³Ñĥ

-0.14

olin

-0.14

POSITIVE LOGITS

eket

0.15

akukan

0.15

0.14

atatype

0.14

binations

0.14

 Combination

0.14

-license

0.14

erez

0.14

eh

0.14

nev

0.13

Activations Density 0.002%

references to combinations or packages of products or items

No Comments

No Known Activations

references to combinations or packages of products or items

No Comments

No Known Activations