INDEX

Explanations

connections to health-related conditions or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

holes

-0.18

ÑĤÑĢÐ¾Ð½

-0.15

Dealer

-0.15

vak

-0.14

conte

-0.14

ikh

-0.14

Gol

-0.14

aho

-0.14

ignum

-0.14

opor

-0.14

POSITIVE LOGITS

wil

0.17

 Rudd

0.15

ippo

0.15

our

0.15

ibern

0.14

orf

0.14

.infinity

0.14

ollo

0.14

Activations Density 0.048%

connections to health-related conditions or statistics

No Comments

No Known Activations