INDEX

Explanations

references to academic journals and their articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Sticky

-0.16

.nasa

-0.15

éĩİ

-0.15

iola

-0.14

efeller

-0.14

çŁ

-0.14

rub

-0.14

tua

-0.14

ochen

-0.14

Topics

-0.14

POSITIVE LOGITS

 volume

0.16

 Lambert

0.15

 lone

0.14

_paper

0.14

 Volume

0.14

PRINTF

0.14

quier

0.14

è¦Ĩ

0.13

 Ð¾Ð±Ð»

0.13

Ð¾ÐºÑĥ

0.13

Activations Density 0.102%

references to academic journals and their articles

No Comments

No Known Activations