INDEX

Explanations

specific dates and numerical values related to occurrences or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

inia

-0.16

erea

-0.15

reed

-0.14

 ç¼

-0.14

gue

-0.14

voie

-0.14

bero

-0.14

uja

-0.14

ionage

-0.14

anden

-0.14

POSITIVE LOGITS

gro

0.17

 Kund

0.16

.Keyboard

0.16

 grav

0.14

 Decomp

0.14

eper

0.14

å¾ģ

0.14

mey

0.13

aurus

0.13

ulu

0.13

Activations Density 0.063%

specific dates and numerical values related to occurrences or entities

No Comments

No Known Activations