INDEX

Explanations

references to specific months and their associated events or data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

imore

-0.18

appa

-0.16

uze

-0.16

uslim

-0.15

|unique

-0.15

iets

-0.14

dle

-0.14

ÙĨÛĮÙĨ

-0.14

ÐµÑĤÐ°

-0.14

estroy

-0.14

POSITIVE LOGITS

eneric

0.15

Daw

0.15

ovic

0.15

TRACE

0.15

QT

0.14

.bd

0.14

.Trace

0.13

 ComVisible

0.13

 Rena

0.13

czy

0.13

Activations Density 0.052%

references to specific months and their associated events or data points

No Comments

No Known Activations