INDEX

Explanations

possessive forms and references to specific individuals 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

llib

-0.15

utenberg

-0.15

Mai

-0.15

gaben

-0.14

lain

-0.14

utherland

-0.14

Î¿Î½

-0.14

kos

-0.14

æŀľ

-0.13

uir

-0.13

POSITIVE LOGITS

stell

0.17

.toObject

0.15

ÄĽle

0.14

;break

0.14

ë§ī

0.14

Hol

0.14

neum

0.14

 Rede

0.13

 ÏĢÎ±

0.13

Activations Density 0.739%

possessive forms and references to specific individuals or entities

No Comments

No Known Activations