INDEX

Explanations

technical terms and structures related to programming and data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ToJson

-0.14

andi

-0.14

\Blueprint

-0.13

ginas

-0.13

iji

-0.13

å´İ

-0.13

ucas

-0.13

azi

-0.13

mile

-0.13

Fold

-0.13

POSITIVE LOGITS

 indem

0.14

 VÅ¡ech

0.14

kie

0.14

(done

0.14

Ø±Ø§Øª

0.14

conte

0.14

gren

0.13

ired

0.13

ateria

0.13

earing

0.13

Activations Density 0.260%

technical terms and structures related to programming and data handling

No Comments

No Known Activations