INDEX

Explanations

terms related to improvisation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

.scalablytyped

-0.17

rint

-0.16

ISMATCH

-0.15

ETCH

-0.15

ÑĳÐ½

-0.14

erras

-0.14

ounder

-0.14

ierz

-0.14

IED

-0.14

FILENAME

-0.14

POSITIVE LOGITS

ise

0.17

ellan

0.15

 Zheng

0.14

-made

0.14

æĺ

0.13

kh

0.13

heit

0.13

á»ģn

0.13

ature

0.13

Activations Density 0.010%

terms related to improvisation

No Comments

No Known Activations