INDEX

Explanations

numerical data and references related to measurements or specifications

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

loy

-0.16

egan

-0.15

adam

-0.14

affles

-0.14

 ç·

-0.14

ool

-0.14

.union

-0.14

ucz

-0.14

Gaz

-0.14

izont

-0.14

POSITIVE LOGITS

ibold

0.18

çĽ¸å½ĵ

0.15

 Clip

0.14

ãĤ¹ãĤ¿ãĥ¼

0.14

.addValue

0.14

ashi

0.14

Ä±rak

0.14

issing

0.14

ARAM

0.14

inaire

0.14

Activations Density 0.164%

numerical data and references related to measurements or specifications

No Comments

No Known Activations