INDEX

Explanations

proper nouns and significant names related to places and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

[sizeof

-0.14

ãģ¦ãĤĭ

-0.14

Ð»Ð¾

-0.14

æķ

-0.14

tro

-0.14

âĢĲ

-0.13

uit

-0.13

jur

-0.13

Gaw

-0.13

ova

-0.13

POSITIVE LOGITS

mma

0.17

edom

0.17

elong

0.17

arth

0.17

 (“

0.16

 Ø§Ø®ØªØµ

0.16

(KP

0.15

(AF

0.15

 abbreviated

0.15

(SS

0.15

Activations Density 0.011%

proper nouns and significant names related to places and institutions

No Comments

No Known Activations

proper nouns and significant names related to places and institutions

No Comments

No Known Activations