INDEX

Explanations

terms related to reviews and summaries of events or media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

AFX

-0.15

YRO

-0.15

EZ

-0.14

uvre

-0.14

 è«

-0.14

odie

-0.14

Dice

-0.14

Î¯

-0.13

ETCH

-0.13

sip

-0.13

POSITIVE LOGITS

0.15

 Pant

0.14

hind

0.14

zers

0.14

Sno

0.14

 Mats

0.14

uni

0.14

argout

0.14

Activations Density 0.083%

terms related to reviews and summaries of events or media

No Comments

No Known Activations