INDEX

Explanations

categorization tags and structural elements in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

[OF

-0.17

vor

-0.15

phylum

-0.15

 Fare

-0.15

adiens

-0.14

VOKE

-0.14

.Persistence

-0.14

us

-0.14

arend

-0.13

edium

-0.13

POSITIVE LOGITS

Ã±ana

0.15

Margins

0.14

 Lang

0.14

/private

0.13

 Holt

0.13

Ã©m

0.13

eneg

0.13

-col

0.13

gnore

0.13

.www

0.13

Activations Density 0.010%

categorization tags and structural elements in documents

No Comments

No Known Activations