INDEX

Explanations

proper nouns and significant keywords in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ãģĹãĤĩ

-0.16

Î²Îµ

-0.15

:UI

-0.14

perl

-0.14

 Kavanaugh

-0.14

 doma

-0.14

Ð½Ð°ÑĢÑĥÐ¶

-0.13

bles

-0.13

anager

-0.13

wert

-0.13

POSITIVE LOGITS

zug

0.17

uez

0.16

loud

0.15

INLINE

0.14

Fullscreen

0.13

onet

0.13

ëįķ

0.13

æ²»

0.13

redients

0.13

Activations Density 0.092%

proper nouns and significant keywords in various contexts

No Comments

No Known Activations