INDEX

Explanations

instances of the word "further" and related positioning or degree terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

andr

-0.18

.DataTable

-0.16

.SDK

-0.16

 Wings

-0.15

earer

-0.15

à¸£à¸¡

-0.15

awah

-0.15

Â¯ÃĤ

-0.15

æµħ

-0.14

ogo

-0.14

POSITIVE LOGITS

nicos

0.16

ataires

0.16

elas

0.16

ãĥ«ãĥī

0.16

 Burton

0.15

atum

0.15

ëĤľ

0.15

ataire

0.15

ATCH

0.15

outine

0.15

Activations Density 0.016%

instances of the word "further" and related positioning or degree terms

No Comments

No Known Activations