INDEX

Explanations

proper nouns related to authors and literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

iro

-0.15

lip

-0.14

 çī

-0.14

Jag

-0.14

oko

-0.13

 unchecked

-0.13

 Trinidad

-0.13

prak

-0.13

cie

-0.13

ÙĳÙĩ

-0.13

POSITIVE LOGITS

_pcm

0.15

chnitt

0.15

ymes

0.14

rani

0.14

rana

0.14

idy

0.14

Äįka

0.14

allet

0.14

theses

0.14

 vill

0.14

Activations Density 0.031%

proper nouns related to authors and literary works

No Comments

No Known Activations