INDEX

Explanations

technical terms and processes related to querying and filtering data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ez

-0.14

-Core

-0.14

ifton

-0.14

 placement

-0.14

Gig

-0.14

-0.13

SSIP

-0.13

 corn

-0.13

ãģ£

-0.13

 placements

-0.13

POSITIVE LOGITS

ÑĢÐ°Ð¶

0.16

needle

0.15

duct

0.15

Ø§ÙĬØ§

0.15

isy

0.15

 Filtering

0.15

.mime

0.15

 ìłķê·ľ

0.15

 filtering

0.14

 specifically

0.14

Activations Density 0.171%

technical terms and processes related to querying and filtering data

No Comments

No Known Activations