INDEX

Explanations

the word "catalog" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Anonymous

-0.16

 Skip

-0.16

skou

-0.15

 skip

-0.15

swire

-0.14

onth

-0.14

 cons

-0.14

Skip

-0.14

annies

-0.14

hÃ¡

-0.13

POSITIVE LOGITS

elli

0.17

enate

0.16

ÑĢÐ¸Ñģ

0.15

ris

0.15

 yÄ±k

0.15

tec

0.14

tvrt

0.14

rezent

0.14

CppClass

0.14

.DOM

0.14

Activations Density 0.003%

the word "catalog" and its variations

No Comments

No Known Activations