INDEX

Explanations

references to iconic and legendary items or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

æµ¦

-0.16

uch

-0.16

ussen

-0.15

iot

-0.15

umble

-0.15

inspace

-0.15

ncy

-0.15

mps

-0.15

onis

-0.14

Ø¡

-0.14

POSITIVE LOGITS

ized

0.17

äººçī©

0.16

nect

0.15

ingles

0.15

ponge

0.13

orable

0.13

èŃĺ

0.13

nection

0.13

noop

0.13

/local

0.13

Activations Density 0.021%

references to iconic and legendary items or symbols

No Comments

No Known Activations