INDEX

Explanations

specifications and features of products, particularly automotive ones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Angiospermae

-0.16

yer

-0.15

pcs

-0.15

izi

-0.14

isible

-0.14

iah

-0.14

azy

-0.14

Ð¸ÑĤÐ¸

-0.14

idges

-0.14

neo

-0.14

POSITIVE LOGITS

 Bucket

0.15

-badge

0.15

stk

0.15

ogg

0.15

 Cloth

0.14

CERT

0.14

moon

0.14

 moon

0.14

 Moon

0.14

ijke

0.14

Activations Density 0.010%

specifications and features of products, particularly automotive ones

No Comments

No Known Activations