INDEX

Explanations

nouns and descriptors related to family

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

alm

-0.16

GG

-0.15

ton

-0.15

ourg

-0.14

aset

-0.14

-Origin

-0.14

ubre

-0.14

-0.13

_MEDIA

-0.13

POSITIVE LOGITS

_NC

0.16

ATTER

0.16

rame

0.16

 aras

0.15

Å¾i

0.15

YRO

0.14

Ã¡li

0.14

 Kurum

0.14

kers

0.14

DRV

0.14

Activations Density 0.006%

nouns and descriptors related to family

No Comments

No Known Activations