INDEX

Explanations

the preposition "in" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

berapa

-0.16

andum

-0.15

kola

-0.15

notated

-0.14

Hir

-0.14

aeda

-0.14

orem

-0.14

emoc

-0.13

ilet

-0.13

iÃªu

-0.13

POSITIVE LOGITS

ients

0.20

iates

0.16

ess

0.15

enk

0.15

sembles

0.15

ses

0.14

woke

0.14

elt

0.14

ently

0.14

Activations Density 0.164%

the preposition "in" and its variations in various contexts

No Comments

No Known Activations