INDEX

Explanations

discussions about performance metrics and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

imm

-0.15

TabControl

-0.14

ilin

-0.14

 Truy

-0.14

.jpa

-0.14

 Town

-0.14

chwitz

-0.13

Std

-0.13

ãĤ¿ãĥ³

-0.13

 numel

-0.13

POSITIVE LOGITS

bab

0.16

AWN

0.16

æĭ¥

0.15

auer

0.14

Ø³Ùĩ

0.14

izzie

0.14

nad

0.14

/apimachinery

0.13

Ø±Øª

0.13

anced

0.13

Activations Density 0.276%

discussions about performance metrics and evaluations

No Comments

No Known Activations