INDEX

Explanations

references to cultural institutions and historical figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

oux

-0.18

Dispose

-0.15

ICODE

-0.15

MouseMove

-0.15

esome

-0.15

ï»¿#

-0.15

idge

-0.14

ospace

-0.14

verty

-0.14

oli

-0.14

POSITIVE LOGITS

Pam

0.16

reon

0.16

umnos

0.15

umba

0.14

.median

0.14

Trip

0.14

losures

0.14

tot

0.14

 Trip

0.14

Activations Density 0.144%

references to cultural institutions and historical figures

No Comments

No Known Activations