INDEX

Explanations

descriptors of spaces and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

orman

-0.17

ivan

-0.16

IDS

-0.14

ãĥ¼ãĥį

-0.14

ÑĢÑĥÑģ

-0.14

uxt

-0.13

adors

-0.13

ukt

-0.13

iez

-0.13

POSITIVE LOGITS

Ø§Ø²ÙĦ

0.15

/embed

0.14

ãĥ³ãĥĩ

0.13

ÑĤÐ°Ð¿

0.13

icap

0.13

etre

0.13

Äįin

0.13

iday

0.13

.elements

0.12

alnÄ±z

0.12

Activations Density 0.511%

descriptors of spaces and their features

No Comments

No Known Activations