INDEX

Explanations

numerical data or statistical figures related to events or phenomena

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

nell

-0.15

ëĭ¤ê³ł

-0.15

ozo

-0.15

ics

-0.15

icken

-0.15

py

-0.15

edd

-0.14

ÛĮÙĨ

-0.14

 Sext

-0.14

don

-0.13

POSITIVE LOGITS

 latter

0.16

led

0.16

vise

0.16

ngr

0.16

lessly

0.16

 ÂłÂł ÂłÂł ÂłÂł ÂłÂł

0.16

rophe

0.15

rous

0.15

coat

0.15

ulance

0.15

Activations Density 0.178%

numerical data or statistical figures related to events or phenomena

No Comments

No Known Activations