INDEX

Explanations

prominent nouns and adjectives that indicate specific qualities or notable subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ãģĹãĤĩ

-0.16

ampo

-0.15

anga

-0.14

:č↵č↵

-0.14

andi

-0.13

áºµ

-0.13

enkins

-0.13

Yue

-0.13

aliz

-0.13

 Zaman

-0.13

POSITIVE LOGITS

 recent

0.37

 recently

0.37

recent

0.34

 lately

0.31

Recently

0.29

 Recently

0.28

 Recent

0.26

Recent

0.23

æľĢè¿ĳ

0.21

_recent

0.21

Activations Density 0.032%

prominent nouns and adjectives that indicate specific qualities or notable subjects

No Comments

No Known Activations