INDEX

Explanations

occurrences of the preposition "in" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

cia

-0.15

ytt

-0.14

Ø«Ø§ÙĦ

-0.13

ponible

-0.13

 morph

-0.13

IDS

-0.13

planation

-0.13

-ended

-0.13

 mechan

-0.13

 puff

-0.13

POSITIVE LOGITS

aint

0.27

registr

0.20

tron

0.20

ÑģÑı

0.17

lish

0.17

rej

0.17

ly

0.16

lej

0.15

_usec

0.15

jun

0.15

Activations Density 0.004%

occurrences of the preposition "in" and its variations in different contexts

No Comments

No Known Activations