INDEX

Explanations

words indicating presence and quantity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Ð°Ð»Ñİ

-0.17

.cod

-0.15

.codes

-0.15

_LOADED

-0.14

ODE

-0.14

agar

-0.14

alet

-0.14

 Dimension

-0.14

POSITIVE LOGITS

cron

0.16

fork

0.15

Ð»Ð¸Ð²Ð°

0.14

utas

0.14

acio

0.14

 fork

0.14

/framework

0.14

à¥įà¤Ĺà¤¤

0.14

lotte

0.13

CONDS

0.13

Activations Density 0.005%

words indicating presence and quantity

No Comments

No Known Activations