INDEX

Explanations

terms related to professional and academic context, particularly focusing on evaluation and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

tvrt

-0.18

ahun

-0.18

hani

-0.18

iren

-0.15

 purely

-0.15

TickCount

-0.14

áº¡n

-0.14

 Ð¢Ð°ÐºÐ¸Ð¼

-0.14

 Pretty

-0.14

 Either

-0.14

POSITIVE LOGITS

 especially

0.61

 especialmente

0.56

 particularly

0.54

especially

0.53

å°¤

0.49

particularly

0.44

çī¹åĪ«

0.44

 besonders

0.44

 particular

0.42

 specifically

0.40

Activations Density 0.222%

terms related to professional and academic context, particularly focusing on evaluation and achievements

No Comments

No Known Activations