INDEX

Explanations

variations of the word "sort" 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 @ 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

orry

-0.16

zier

-0.15

aters

-0.15

hip

-0.15

andest

-0.15

ossier

-0.15

IMAL

-0.15

burg

-0.14

errupted

-0.14

hower

-0.14

POSITIVE LOGITS

taÅŁ

0.17

folio

0.16

iller

0.16

ilege

0.15

ship

0.15

ngo

0.15

 Druh

0.15

rÃ¥

0.14

icultural

0.14

okus

0.14

Activations Density 0.015%

variations of the word "sort" in different contexts

No Comments

No Known Activations