INDEX

Explanations

references to web document types and related parameters

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

 Phon

-0.14

meth

-0.14

 fled

-0.14

Gew

-0.13

anter

-0.13

 Soph

-0.13

 Catch

-0.13

ucer

-0.13

 Phil

-0.13

ords

-0.13

POSITIVE LOGITS

anko

0.19

.cgi

0.18

leigh

0.17

raki

0.16

elt

0.15

cion

0.15

å¾ģ

0.15

rolling

0.14

alien

0.14

enary

0.14

Activations Density 0.001%

references to web document types and related parameters

No Comments

No Known Activations