INDEX

Explanations

terms related to acceleration and rapid processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ality

-0.17

 McCabe

-0.16

lug

-0.15

asu

-0.15

soever

-0.15

esty

-0.14

iculty

-0.14

akes

-0.14

RIES

-0.14

mul

-0.14

POSITIVE LOGITS

/de

0.20

oni

0.18

 paced

0.17

idia

0.16

ased

0.16

 pace

0.16

ator

0.16

ometer

0.16

-paced

0.16

pace

0.15

Activations Density 0.021%

terms related to acceleration and rapid processes

No Comments

No Known Activations