INDEX

Explanations

references to generations and terms within contexts involving families or structured systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

UGIN

-0.16

ota

-0.16

erken

-0.15

chk

-0.15

cbc

-0.14

/ros

-0.14

ë²Ķ

-0.14

 ersten

-0.14

Ã©ric

-0.14

 first

-0.14

POSITIVE LOGITS

undred

0.17

otics

0.16

0.15

 Syndrome

0.15

ãĢģäºĮ

0.15

axon

0.14

.ibatis

0.14

ãĢģä¸ī

0.14

-third

0.14

/single

0.14

Activations Density 0.124%

references to generations and terms within contexts involving families or structured systems

No Comments

No Known Activations