INDEX

Explanations

occurrences of prepositions and related phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

insky

-0.17

omu

-0.16

OMPI

-0.15

insk

-0.15

amodel

-0.15

adol

-0.14

icit

-0.14

IALOG

-0.14

archy

-0.14

 Ballard

-0.14

POSITIVE LOGITS

avers

0.16

encil

0.16

ichel

0.16

late

0.15

åĲ«

0.14

 kÃª

0.14

 æĻ

0.14

ween

0.14

oux

0.14

weeney

0.14

Activations Density 0.000%

occurrences of prepositions and related phrases

No Comments

No Known Activations