INDEX

Explanations

references to structured categories or levels, particularly related to hierarchical classifications

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

.getSeconds

-0.17

\grid

-0.15

ieren

-0.15

 relieved

-0.15

oose

-0.15

stown

-0.14

 relieve

-0.14

/ion

-0.13

stre

-0.13

pron

-0.13

POSITIVE LOGITS

 Shan

0.15

istrovstvÃŃ

0.15

UNET

0.15

ANC

0.15

 Miche

0.14

 sunk

0.14

dling

0.14

issy

0.14

afx

0.14

IFF

0.14

Activations Density 0.010%

references to structured categories or levels, particularly related to hierarchical classifications

No Comments

No Known Activations